EP4179469A1 - Dispositif électronique et procédé de traitement de données à base de réseaux génératifs inversibles, système électronique de détection et programme d'ordinateur associés - Google Patents
Dispositif électronique et procédé de traitement de données à base de réseaux génératifs inversibles, système électronique de détection et programme d'ordinateur associésInfo
- Publication number
- EP4179469A1 EP4179469A1 EP21742808.5A EP21742808A EP4179469A1 EP 4179469 A1 EP4179469 A1 EP 4179469A1 EP 21742808 A EP21742808 A EP 21742808A EP 4179469 A1 EP4179469 A1 EP 4179469A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- component
- task
- data
- module
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0475—Generative networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Definitions
- the present invention relates to an electronic data processing device, as well as a data processing method implemented by such an electronic processing device.
- the invention also relates to an electronic system for detecting object(s), comprising a sensor, such as an image sensor(s), and such an electronic processing device, each datum to be processed being an object detected in a respective image.
- the invention also relates to a computer program comprising software instructions which, when executed by a computer, implement such a processing method.
- the invention therefore relates to the field of machine learning, in particular that of continuous learning based on generative neural networks, in particular for data processing, such as data classification and learning of latent features.
- neural network we mean an artificial neural network known in itself.
- the invention offers various applications, such as the classification or identification of objects previously detected by an object detector, making it possible, for example, to learn the identities of people whose faces have been detected by a face detector.
- Another application is an unsupervised, automatic feature learning system, for example a system which is autonomously and continuously trained on human voice data around it, and the learned features are then used to pre-process data for a specialized learning system on the voice of a certain person.
- a neural network for data processing and in particular for classification
- a task also called a class when used for data classification, such as a first task, or first class
- another task namely a second task, or second class
- the neural network will forget the information learned about the first task and then be unable to perform the task again.
- first task phenomenon is also known as catastrophic forgetting.
- neural networks for data processing and in particular for classification, are then trained simultaneously on a plurality of tasks, or classes, examples representing these different tasks then having to be distributed homogeneously in a set training data.
- these neural networks are typically trained on a number of tasks which is fixed at the start of their learning.
- EWC Elastic Weight Consolidation
- SI English Synaptic Intelligence
- Generative models aim to represent an input space X in an output space Y, by defining for example a joint probability law or bijective functions for all possible variables, i.e. for the variables of l output space Y, also called output variables and corresponding to the data to be predicted; for the variables of the input space X, also called input variables and corresponding to the data received as input from the generative model; and for the variables of an unobserved space, also called latent space H, also denoted Z, these unobserved auxiliary variables then also being called latent or hidden variables. These latent variables then correspond to vectors of the latent space H, also called latent vectors.
- the output space Y corresponds to the task space, and the output variables then represent identifiers, or labels (from l 'English task label), of tasks associated with the input data.
- Such methods are often considered as implementing an approach called generative replay (or pseudo-rehearsal).
- the artificial data produced are used in combination with the data of a new task to train the neural network or networks implemented for the processing of data, and in particular for the classification of these data.
- the paper “Continuai Unsupervised Representation Learning” by Rao et al, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) describes an example of such a generative retraining process.
- the object of the invention is therefore to propose an electronic data processing device, and an associated processing method, making it possible to offer a better solution to the phenomenon of catastrophic forgetting by better representing the tasks, or classes, and then d 'learn characteristics that are more discriminating.
- an electronic data processing device comprising:
- an acquisition module configured to acquire a set of data(s) to be processed
- a calculation module including a plurality of components, each associated with a respective task, each component being configured to implement an invertible neural network to calculate a vector in a latent space, called a latent vector, from the set of data) ;
- a determination module configured to determine a task for each datum, by:
- the electronic processing device offers continuous learning based on generative neural networks, the networks of the calculation module further being invertible neural networks (normalizing flow) which then each learn a bijective function between the input space X and the latent space H.
- the latent space H is then distributed according to a probabilistic distribution function of the same dimension than that of the input space X, each probabilistic distribution function being for example a multidimensional Gaussian.
- the possibility of inverting the neural network of each component then makes it possible to express the likelihood function of the data of the input space X more easily according to the values of the vectors of the space latent h.
- Invertible networks also allow an exact calculation of the likelihood score of the data of the input space X according to the probabilistic distribution function px of the input space X. Also, if the likelihood score of a sample is inconsistent for the component associated with the assigned task, for example if the likelihood score deviates too much from the mean score observed during the learning of said component, this sample is considered to be of unknown task.
- the electronic processing device then makes it possible to additionally carry out a detection of unknown task(s), or unknown class(es).
- an invertible neural network for each component of the calculation module makes it possible to use the same and unique neural network for encoding from the input space X to the latent space H, and for the decoding from the latent space H to the input space X, this decoding typically making it possible to create artificial examples of data, for the subsequent retraining of the neural networks of the components.
- invertible networks Another advantage of invertible networks is the possibility of implementing the gradient back-propagation algorithm with less memory resources, since the activations of each neuron are reconstructable from the exit from the network. This makes it possible to recalculate the activations in parallel during a back-propagation phase, which avoids having to save the activations of each neuron during an inference phase.
- the invention is then particularly suitable for the implementation of a continuous learning system with fewer memory resources, such as an embedded system.
- the parameters of the neural network of each component are capable of being optimized using a maximum likelihood estimation method on the data of the input space X.
- the neural network of each component is learned using a back-propagation algorithm for calculating the gradient of each parameter of the network according to a cost function, the cost function typically comprising a likelihood term, such as a logarithmic likelihood term.
- the electronic processing device comprises one or more of the following characteristics, taken in isolation or in all technically possible combinations:
- the device further comprises a feedback module configured to store in a buffer memory each unknown task datum, and to trigger the creation of a new task if the number of data stored in the buffer memory is greater than a predefined number; the calculation module then being configured to include a new component associated with the new task, the learning of the new component being carried out from said data stored in the buffer memory;
- the invertible neural network of each component includes parameters, such as weights; said parameters being optimized via a maximum likelihood method; the learning of said network being preferably carried out via a back-propagation algorithm for calculating the gradient of each parameter; the learning of said network preferably still being continuous, in particular carried out after each processing of data(s);
- the device further comprises a feature extraction module connected between the acquisition module and the calculation module, the extraction module being configured to implement at least one neural network to convert the data set (s) in a simplified representation, by extracting one or more characteristics common to the plurality of tasks; each neural network of the extraction module preferably being invertible; the extraction module preferably further comprising a first extractor configured to implement a neural network with fixed weights following training of said network and a second extractor configured to implement a neural network with trainable weights via continuous learning, such as learning carried out after each processing of data(s), in particular via a reverse propagation algorithm;
- the determination module is further configured to generate a vector of random or pseudo-random number(s) corresponding to the distribution of the latent space of one of the components, then to propagate said vector of inversely via the corresponding invertible neural network, in order to create an artificial example of data(s), a task identifier associated with this artificial example being an identifier of said component; said vector preferably being propagated in an inverse manner towards the calculation module or else towards a retraining module distinct from the calculation module;
- the device further comprises a retraining module configured to receive the vector generated by the determination module and to supply at least one artificial example of data(s) and its identifier to the component(s) of the associated calculation module (s) to the same identifier, said component(s) being to be trained again, the retraining module comprising a copy of each component to be trained again;
- the retraining module further comprises a copy of the second extractor, the retraining module then being further configured to provide at least one artificial example of data(s) to the second extractor of the extraction module;
- the device is configured to perform unsupervised learning of tasks, each component of the calculation module being configured to calculate a vector in the latent space for each new datum, the latent space then comprising latent vectors for this new datum , an identifier of the component also being associated with each calculated latent vector;
- the determination module is further configured to modify the identifiers of components from a batch of identified examples, a respective identifier being associated with each example, by assigning for each example its identifier to the component presenting the likelihood score the higher, the component(s) not having an identifier assigned after taking into account all the examples of the batch being ignored;
- the likelihood score is a logarithmic score; the likelihood score preferably comprising the following logarithmic term: l°g [PH (i (*))].
- H represents a space of latent vectors, also called latent space
- PH represents a probabilistic distribution function of the latent space H
- k is an integer index representing each component, k being typically between 1 and P, with P representing the number of components, P 3 2,
- the assessed likelihood score is inconsistent for the component associated with the assigned task if the difference between the assessed likelihood score and an average likelihood score for said component is greater than a threshold; said threshold preferably being a predefined value for each component, or even a percentage of an average value observed for each component; a so-called out-of-distribution detection method is applied as a variant to the likelihood scores evaluated for the detection of unknown sample(s);
- the determination module is further configured to transmit the latent vectors to another electronic data processing device, such as a k-NN classifier or another neural network;
- the acquisition module is further configured to carry out a normalization of the set of data(s) and/or an enrichment of the set of data(s), for example via one or more random angle rotations.
- the invention also relates to an electronic system for detecting object(s), the system comprising a sensor, such as an image(s) sensor, a sound sensor or even an object detection sensor, and an electronic data processing device connected to the sensor, the electronic processing device being as defined above, and each data to be processed is an object detected in an image.
- a sensor such as an image(s) sensor, a sound sensor or even an object detection sensor
- an electronic data processing device connected to the sensor, the electronic processing device being as defined above, and each data to be processed is an object detected in an image.
- the invention also relates to a data processing method, implemented by an electronic processing device and comprising the following steps:
- the invention also relates to a computer program comprising software instructions which, when executed by a computer, implement a processing method, as defined above.
- FIG. 1 is a schematic representation of an electronic system for detecting objects according to the invention, comprising a sensor and an electronic data processing device, connected to the sensor;
- FIG. 2 is a more detailed schematic representation of the electronic processing device of Figure 1, comprising in particular a calculation module including a plurality of components, each being associated with a respective task and configured to implement an invertible neural network to calculate a vector in a latent space from a set of data(s) to be processed, according to a first embodiment;
- a calculation module including a plurality of components, each being associated with a respective task and configured to implement an invertible neural network to calculate a vector in a latent space from a set of data(s) to be processed, according to a first embodiment
- FIG. 3 is a schematic representation of an example of implementation of the invertible neural networks of the components of the calculation module of Figure 2, these invertible neural networks also being optionally connected to the invertible neural network of a module feature extraction included in the electronic processing device of FIGS. 1 and 2, in addition to the calculation module;
- FIG. 4 is a view similar to that of Figure 2, according to a second embodiment of the invention, in which the electronic processing device further comprises a retraining module configured to supply from a latent vector , at least one artificial example and its identifier, to the component(s) of the calculation module associated with the same identifier as that of the artificial example, said component(s) being to be trained again, and the module retraining comprising a copy of each component to be retrained; and
- FIG. 5 is a flowchart of a data processing method according to the invention, the method being implemented by the electronic processing device of Figure 1.
- task or even class, we mean a grouping of similar data, or of the same type, and each task is associated with an identifier, or label, task label.
- identifier or label
- task label means a grouping of similar data, or of the same type, and each task is associated with an identifier, or label, task label.
- task and class are considered to be synonymous within the meaning of the present invention.
- object is meant a concrete realization of a class or task, for example a physical object, a person, and more generally an element present in a scene captured by a sensor, in particular of the type described below.
- the scene is then typically represented in the form of images or videos in the case of an image(s) sensor or an infrared sensor, in sound form in the case of a sound sensor, or even in the form cloud(s) of points in the case of a lidar or radar sensor.
- an electronic detection system 10 is configured to detect one or more objects, not shown, and comprises a sensor 12 and an electronic processing device 14, connected to the sensor 12.
- the electronic detection system 10 forms, for example, a face detector able to recognize the faces of previously identified persons and/or to detect the faces of unknown persons, that is to say faces of persons who have not been previously identified.
- the electronic processing device 14 then makes it possible to learn the identities of the people detected, and also to identify unknown people.
- the sensor 12 is known per se, and is for example an image sensor (s) configured to take one or more images of a scene, and transmit them to the electronic processing device 14.
- the senor 12 is a sound sensor, an object detection sensor, such as a lidar sensor, a radar sensor, an infrared sensor, a capacitive proximity sensor, an inductive proximity sensor, a proximity sensor Hall effect or even a presence sensor, configured to acquire a characteristic signal depending on the presence or absence of object(s), then to transmit it to the electronic processing device 14.
- an object detection sensor such as a lidar sensor, a radar sensor, an infrared sensor, a capacitive proximity sensor, an inductive proximity sensor, a proximity sensor Hall effect or even a presence sensor, configured to acquire a characteristic signal depending on the presence or absence of object(s), then to transmit it to the electronic processing device 14.
- the electronic processing device 14 is configured to process a set of data(s), the set of data(s) typically corresponding to one or more signals picked up by the sensor 12.
- the electronic processing device 14 is then typically configured to interpret a scene captured by the sensor 12, that is to say to identify and/or to recognize a type of one or more elements - such as people or physical objects - present in the captured scene and corresponding to the signal or to the signals picked up by the sensor 12.
- the electronic processing device 14 comprises a module 16 for acquiring the set of data(s) to be processed; a calculation module 18 including a plurality of components 20, visible in Figures 2 to 4, each associated with a respective task, each component 20 being capable of calculating a vector in a latent space H, called latent vector h k , from the set of data(s) ; and a module 22 for determining a task for each datum, from the calculated latent vector h k.
- the electronic processing device 14 further comprises a feedback module 24 configured to store in a buffer memory 26, visible in FIG. 2, each unknown task datum and to trigger, if necessary, the creation of a new task.
- the electronic processing device 14 further comprises a feature extractor module 28, connected between the acquisition module 16 and the calculation module 18, the extraction 28 being capable of extracting one or more characteristics common to several tasks in order to transform the set of data(s) into a simplified representation.
- the electronic processing device 14 further comprises a retraining module 30 configured to generate, from a vector of random or pseudo-random number(s) corresponding to the distribution in the latent space of one of the components, at least one artificial example of data(s) and its identifier, and then provide them to the component(s) 20 associated with the same identifier, said component(s) 20 being to be trained again, the retraining module 30 comprising a copy of each component 20 to be trained again.
- the electronic processing device 14 comprises an information processing unit 40 formed for example of a memory 42 and a processor 44 associated with the memory 42.
- the acquisition module 16, the calculation module 18 and the determination module 22, as well as optionally the feedback module 24, the extraction module 28 and/or the retraining module 30, are each produced in the form of software, or a software brick, executable by the processor 44.
- the memory 42 of the electronic processing device 14 is then capable of storing software for acquiring the set of data(s) to be processed, software for calculating the latent vector for each component from the set of data(s) and software for determining a task for each data from the calculated latent vectors.
- the memory 42 of the electronic processing device 14 is capable of storing feedback software capable of storing in the buffer memory 26 each unknown task datum and of triggering, if necessary, the creation of a new task, a software extraction of characteristics common to several tasks in order to convert the set of data(s) into a simplified representation, and retraining software capable of providing, from a random or pseudo-random vector corresponding to the distribution of the latent space of one of the components, at least one artificial example of data(s) and its identifier, this to the component(s) with the same identifier as that of the generated artificial example.
- the processor 44 is then capable of executing each of the software programs among the acquisition software, the calculation software and the determination software, as well as, as an optional complement, the feedback software, the extraction software and/or the retraining.
- the acquisition module 16, the calculation module 18 and the determination module 22, as well as in optional addition the feedback module 24, the extraction module 28 and/or the retraining module 30, are each made in the form of a programmable logic component, such as an FPGA (English Field Programmable GateArray), or in the form of a dedicated integrated circuit, such as an ASIC (English Application Specifies Integrated Circuit).
- a programmable logic component such as an FPGA (English Field Programmable GateArray)
- ASIC American Application Specifies Integrated Circuit
- the electronic processing device 14 When the electronic processing device 14 is produced in the form of one or more software, that is to say in the form of a computer program, it is also capable of being recorded on a medium, not shown, computer readable.
- the computer-readable medium is, for example, a medium capable of storing electronic instructions and of being coupled to a bus of a computer system.
- the readable medium is an optical disc, a magneto-optical disc, a ROM memory, a RAM memory, any type of non-volatile memory (for example EPROM, EEPROM, FLASH, NVRAM), a magnetic card or an optical card.
- EPROM EPROM
- EEPROM electrically erasable programmable read-only memory
- FLASH erasable programmable read-only memory
- NVRAM any type of non-volatile memory
- the acquisition module 16 is configured to acquire the set of data(s) to be processed.
- the data space to which this set of data(s) belongs is denoted X
- each set of data(s) acquired is denoted x, and is for example in the form of a vector comprising the or the input data, also called the input vector x.
- the acquisition module 16 is also configured to perform a pre-processing of the acquired data, such as a normalization of the acquired data.
- the acquisition module 16 is further configured to carry out an enrichment of the acquired data, for example by applying one or more random angle rotations to the acquired data in order to generate additional data.
- Compute module 18 includes the plurality of components 20, each associated with a single respective task.
- each component 20 is configured to implement an invertible neural network to calculate from the set of data, such as from the input vector x, a vector in latent space H, also called latent vector h k .
- each component 20 is also then denoted C k , where k is an integer index with a value between 1 and P.
- Each component C k is then configured to calculate the latent vector h k exponent k, as represented in FIG. 2 where the latent vectors h 1 , h 2 , ... h p are then calculated by the calculation module 18 for each input vector x, and more particularly by the respective components Ci, C 2 , ..., Cp.
- Each invertible neural network is configured to learn a one-to-one function between the input data space X and the latent space H, and the latent space H is then constrained to be distributed according to a probabilistic distribution function of dimension equal to that of the input space X.
- the probabilistic distribution function according to which the latent space H is distributed is for example a multidimensional Gaussian, as is that according to which the input space X is distributed.
- Each invertible neural network comprises one or more invertible blocks 32 (coupling layer), where each invertible block 32 represents a one-to-one transform between its input and its output.
- each component 20 of the calculation module 18 comprises an invertible block with four input/output dimensions
- each invertible neural network of a component 20 also includes a scale adaptation layer 34, and the parameters of this adaptation layer 34 can also be trained.
- FIG. 3 also illustrates the connection of several invertible neural networks to a common invertible neural network, when the extraction module 28 comprises one or more invertible neural networks connected one after the other, the last invertible network of this succession then being connected to each of the invertible neural networks associated with the components 20 arranged in parallel.
- the output node of the last common invertible network is connected to the input node of the same dimension of each of the input invertible neural networks of the components 20, as shown in Figure 3.
- the common invertible neural network or networks (represented on the left part of the figure) then play the role of extractor of characteristic(s) common to the plurality of tasks for all the neural networks reversible components 20 (shown on the right side of the figure), which are arranged in parallel to each other and specific to each task.
- the determination module 22 is configured to determine a task for each datum by evaluating, for each component 20, denoted C k , a likelihood score from the corresponding latent vector h k; and by assigning, to said datum, the task with identifier k associated with the component 20 with the highest likelihood score among the plurality of likelihood scores evaluated; and if the assessed likelihood score is inconsistent for the component 20 associated with the assigned task, changing the assigned task to an unknown task.
- Each likelihood score evaluated by the determination module 22 is for example a logarithmic score and each likelihood score then preferably comprises the following logarithmic term (7) where PH represents a probabilistic distribution function of the latent space H, k is an integer index representing each component, k being typically between 1 and P, with P representing the number of components, P 3 2,
- PHW Yld PH d (hd) (8)
- d represents the number of dimensions of the input space X and of the latent space H which is identical for the two spaces, due to the use of networks of reversible neurons.
- the probabilistic distribution function of the input space X satisfies the following equation: dF k (x ) det dx (9) dF k (x ) where the term det dx represents the Jacobian determinant of the transformation function F k (x)
- the logarithmic likelihood score according to equation (10) then includes the logarithmic term of the previous equation (7).
- the invertible neural network of each component 20 comprises parameters Q, the parameters of each component C k then being denoted 0 k , and said parameters are preferably optimized via a maximum likelihood method.
- the learning of the invertible neural network(s) of each component is then preferably carried out via a back-propagation algorithm for calculating the gradient of each parameter Q.
- the training of each network is preferably still continuous, and in particular carried out after each data processing.
- the determination module 22 is then configured to determine the task for each datum, by assigning to said datum the task with index k which is associated with the component with the highest likelihood score among the plurality of scores evaluated, and the identifier, or label, of said task then typically verifies the following equation:
- the identifier of said task is determined according to the following equation:
- the determination of said identifier according to the preceding equation (13) uses a simplified logarithmic likelihood score based only on the latent term of the likelihood score, that is to say on the term logp ⁇ (F fe (x)), and not taking into account the term corresponding to the logarithm of the dF k (x ) Jacobian determinant of the transformation function, i.e. the term log
- the inventors have indeed observed that the use of the single term latent logp # (F fe (x)) makes it possible to obtain better results when the determination of tasks is used for data classification and/or for detection of class boundaries, whereas the use of the full logarithmic likelihood score according to the previous equation (12) is preferable for the optimization of each invertible neural network. They estimate that this is probably due to the fact that the term of the logarithmic likelihood score corresponding to the logarithm of the Jacobian determinant, that is to say the term dF k (x) log
- the probabilistic distribution function PH of the latent space H is generally a factorized standard normal distribution function, such as the distribution function verifying for example the following equation: where ma, and respectively s, represent the mean, and respectively the standard deviation, of the d-dimensional probabilistic distribution function, such as the multidimensional Gaussian.
- the determination module 22 is configured to determine that the assessed likelihood score is inconsistent for the component 20 associated with the assigned task if the difference between the assessed likelihood score and an average likelihood score for said component 20 is greater than a threshold.
- This threshold is for example a predefined value for each component 20, or even a percentage of an average value observed for each component 20.
- the determination module 22 is configured to detect that the assessed likelihood score is inconsistent, and that the assigned task must then be modified into an unknown task by applying a so-called out-of-distribution detection method, also denoted OOD (from the 'English Out-Of-Distribution), with the assessed likelihood score.
- OOD out-of-distribution detection method
- the determination module 22 is further configured to transmit the calculated latent vectors h k to another electronic data processing device, such as a k-NN (K-Nearest Neighbors) classifier, i.e. a classifier (c/ass/7/er) implementing the k nearest neighbors algorithm, or another machine learning algorithm, such as one or more artificial neural networks.
- a k-NN K-Nearest Neighbors
- c/ass/7/er implementing the k nearest neighbors algorithm
- another machine learning algorithm such as one or more artificial neural networks.
- the determination module 22 is further configured to generate a vector of random number(s) or pseudo-random number(s) corresponding to the distribution of the latent space H of one of the components 20, then to propagate said random or pseudo-random vector inversely via the corresponding invertible neural network, that is to say via the invertible neural network of the component corresponding to the distribution of the latent space taken into account, in order to creating an artificial example 52 of data(s), a task identifier associated with this artificial example 52 then being the identifier of said component via which the reverse propagation was carried out.
- the creation of the artificial example 52 is illustrated for the component C 5 , and the reverse propagation of the random or pseudo-random vector is represented by the random vector h s 5 generated by the module of determination 22 destined for component C 5 , then propagated inversely in the direction of the input space X, as represented by the arrows G1, G2 and G3.
- the random or pseudo-random vector that is to say the vector h s 5 in the example of FIG. 2, or even the vector h s 2 in the example of FIG. 4, is propagated inversely to the calculation module 18 as in the example of Figure 2, or to the retraining module 30 separate from the calculation module 20 as in the example of Figure 4.
- the electronic processing device 14 then makes it possible, in other words, to generate samples x s of the learned distribution rc(c,q*) by drawing a random sample from the distribution function of the latent space, and by transferring this random sample to the input space by reverse propagation, i.e. by applying the inverse function F 1 , to the random sample of the function of distribution of the latent space H.
- the preceding equations (15) and (16) correspond to the case where the distribution function of the latent space is a factorized standard equation.
- the feedback module 24 is configured to store in the buffer memory 26 each unknown task datum, that is to say each task datum whose assessed likelihood score is inconsistent, and to trigger the creation of a new task. if applicable.
- the feedback module 24 is for example configured to trigger the creation of a new task if the number of data stored in the buffer memory 26 is greater than a predefined number.
- the calculation module 18 is then configured to include a new component 20 associated with the new task created by the feedback module 24, as represented by the arrow R1 in the examples of figures 2 and 4, and the training of the new component 20 is then performed from said data stored in the buffer memory 26.
- the extraction module 28, connected between the acquisition module 16 and the calculation module 18, is configured to implement at least one neural network to convert the set of data(s), such than the acquired data vector X, in a simplified representation, by then extracting one or more characteristics common to the plurality of tasks.
- Each neural network of the extraction module 28 is preferably an invertible neural network.
- the extraction module 28 advantageously consists of a first extractor 60 configured to implement a neural network with fixed weights following the learning of said network and a second extractor 62 configured to implement a neural network with trainable weights via continuous learning, such as learning performed after each data processing, in particular via a reverse propagation algorithm when the first and second extractors 60, 62 each comprise invertible neural networks.
- the architecture of the electronic processing device 14 is particular in that it comprises two parts, namely a part agnostic to the tasks corresponding to the extraction module 28, and in particular to the first feature extractor 60 and to the second feature extractor 62, and a task-specific part comprising several independent invertible blocks, namely the components 20, which are all connected in parallel to the task-agnostic part.
- This two-part architecture with an agnostic part and a specific part then makes it possible to offer better continuous learning.
- the part specific to the tasks corresponds to high-level components of the distribution to be modeled, and given that their weight are independent, they are not subject to the phenomenon of catastrophic forgetting.
- the task-agnostic part allows it to play the role of extractor of characteristics common to all the components 20, but is however subject to the phenomenon of catastrophic forgetting if the tasks are learned in a sequential manner.
- the task-agnostic part makes it possible to use far fewer parameters, since the task-agnostic features are usable simultaneously by all 20 components that are task-specific.
- each additional task is learned more quickly and with a lower number of examples, being based on characteristics agnostic to existing tasks.
- the characteristics common to the plurality of tasks are symbolized by the functions fo to ÎN-I for the first extractor 60, then by the functions fn to ⁇ MI for the second extractor 62, and the characteristics specific to each task are then symbolized by the functions f M k fwi + A to fi_ k where k represents the identifier of the task.
- the first extractor 60 is configured to implement a composite of the functions fo to ⁇ NI in the sense of inference or learning, that is to say from space of data X towards the latent space H, as represented by the arrows IL1 , IL2 and IL3, and conversely to implement the composition of function f 0 1 to fn 1 in the opposite direction, for example for the generation of examples artificial 52 from the latent space H to the data space X, as represented by the arrows G1 to G3.
- the second extractor 62 is configured to implement a composite of the functions ⁇ N to ⁇ MI in the direction of inference or learning from the data space X to the latent space H, and conversely to implement a composite of the inverse functions Î N 1 to ⁇ M 1 in the direction of generating artificial examples from the latent space H to the data space X.
- each component C k is configured to implement a composite of the specific functions f M k àfi_ k in the direction of inference and learning from the data space X to the latent space H , and conversely only the component associated with the generated random vector, such as the component C 5 in the example of FIG. 2 or even the component C 2 in the example of FIG. 4, is configured to implement in the direction inverts a composite inverse function, such as the composite of inverse functions (f M 5 ) 1 to (fi_ 5 ) 1 in the example of FIG. 2, or such as the composite of inverse functions (f M 2 ) 1 to (fi_ 2 ) 1 in the example of figure 4.
- each latent vector h k verifies the following equation in these examples of FIGS. 2 and 4:
- the composite of the functions fo to ⁇ MI corresponds to the task-agnostic part, that is to say to the optional extraction module 28, and the composition of the functions f M k to fi_ k corresponds to the part specific to the tasks, in this case to the part specific to the task with identifier k, that is to say to the component C k .
- the composite of the inverse functions fo 1 to ⁇ M 1 corresponds to the task-agnostic part, i.e. to the optional extraction module 28, and the composite of the inverse functions (f M k ) 1 to (fi_ k ) 1 corresponds to the task-specific part, in particular to the inverse implementation of the component C k .
- the electronic processing device 14 further comprises the extraction module 28 connected between the acquisition module 16 and the calculation module 18, in particular further comprises the second extractor 62
- the feedback module 24 is configured to transmit new data stored in the buffer memory 26 at the same time to the calculation module 18 for the inclusion of a new component 20 associated with the new task according to the arrow R1; and also to the extraction module 28, in particular to the second extractor 62 whose neural network or networks include trainable weights, the second extractor 62 then also being trained with these data coming from the feedback module 24, as represented by the arrow R2.
- the electronic processing device 14 then offers different applications.
- a first application is the classification of data, and the task or class predicted for each datum to be processed is then determined by searching for the component 20 presenting the highest likelihood score among the plurality of scores evaluated for the different components 20, the determined task then being the one associated with the component having the highest likelihood score.
- the label t of the determined task then verifies for example equation (12), or even preferably equation (13) which does not take into account the volume term, ie which does not take into account the logarithm of the determinant Jacobien, and then provides better results.
- a second application of the electronic processing device 14 according to the invention is the labeling of components, or even the identification of components, such labeling being for example obtained via supervised learning, which then means that the task label t is provided with the datum x, and the calculation module 18 then comprises a single component 20 for each task.
- this labeling of components is carried out in an unsupervised manner, and the processing device 14 is then configured to carry out an unsupervised learning of tasks, each component 20 of the calculation module 18 then being configured to calculate a vector in the latent space H for each new datum, the latent space H then comprising latent vectors h k for this new datum, and an identifier of the component 20 being further associated with each calculated latent vector h k.
- the determination module 22 is for example further configured to modify the component identifiers 20 from a batch of identified examples, a respective identifier being associated with each example; this by assigning for each example its identifier to the component 20 having the highest likelihood score, the component(s) having no assigned identifier after taking into account all the examples of the batch then being ignored.
- the determination module 22 is for example further configured to modify the component identifiers 20 from a batch of identified examples, a respective identifier being associated with each example; this by assigning for each example its identifier to the component 20 having the highest likelihood score, the component(s) having no assigned identifier after taking into account all the examples of the batch then being ignored.
- several components 20 of the calculation module 18 are likely to represent the same task.
- a third application of the electronic processing device 14 is the detection of off-distribution data for the classification and/or for the detection of task boundaries.
- This third application preferably corresponds to unsupervised learning without a previously assigned task label.
- the detection of unknown task(s) or class(es) also allows, when the processing device 14, and in particular its neural networks, are in pure inference mode, and no new component is added, calculating an estimate of a response certainty of the neural network(s).
- the detection of unknown task(s) according to this third application is then carried out, as described above, by detecting that a likelihood score evaluated by the determination module 22 is inconsistent for the component 20 associated with the assigned task, such an inconsistency typically corresponding to a difference between the assessed likelihood score and the average likelihood score for said component greater than a threshold.
- this unknown task(s) detection application is likely to be implemented only after the implementation of a start-up phase during which a certain number of Iterations are performed for each component 20, this until it converges towards the distribution of a respective task, and during this start-up phase no unknown task is likely to be detected.
- the threshold used to detect new task(s), via an inconsistency in the assessed likelihood score is for example a predefined value for each component or else a percentage of an average value observed for each component. In in the latter case, the assessed likelihood score is then considered inconsistent from the moment it deviates from said percentage with respect to the average likelihood score observed for said component.
- the samples which are considered to be unknown are then added to the buffer memory 36, and when the number of unknown samples is greater than the aforementioned predefined number, the determination module 22 considers that the task has changed, and a learning is then performed for the new task, as represented by the arrows R1, R2 and described previously.
- the feedback module 24 is configured to regularly erase the buffer memory 26, for example if after a small number of unknown samples a large number of known examples are encountered again, that is to say associated to already known tasks. Such a regular clearing of the buffer memory 26 by the feedback module 24 then makes it possible to avoid the addition of a new task which would be based on disparate unknown examples obtained over time until the number of data unknowns exceeds the predefined number of triggering the creation of a new task.
- a fourth application of the electronic processing device 14 according to the invention is the autonomous and dynamic addition of components 20 within the calculation module 18. Indeed, as described above, when a new task has been detected, a new component 20 is initialized within the calculation module 18, this for example with random weights, or even with the weights of the component 20 (among those already existing) having the highest likelihood score for the data stored in the buffer memory 26 .
- This new component 20, and if applicable the second extractor 62, is then trained for the number of iterations corresponding to the start-up phase, described previously, for example via an optimization based on the gradients from the data stored in the buffer memory 26, which then allows the new component 20 to converge on the distribution of the new task.
- the start-up phase for learning the new component 20 is carried out until a convergence criterion is reached. checked.
- the electronic processing device 14 also comprises the retraining module 30, the latter being separate from the calculation module 18, and if necessary from the extraction module 28.
- the retraining module 30 is configured to receive the random or pseudo-random vector h s k (such as the vector h s 2 in the example of FIG. 4), generated by the determination module 22 for the component of index k which is to be trained again, and the retraining module 30 is then configured to supply at least one artificial example 52 of data(s) and its identifier, this to the component 20 of the calculation module 18 which is associated with the same identifier k, such as the identifier of value 2 in the example of figure 4.
- the random or pseudo-random vector h s k such as the vector h s 2 in the example of FIG. 4
- the retraining module 30 then comprises a copy of each component 20 which is to be trained again.
- the retraining module 30 further comprises a copy of the second extractor 62, and the retraining module 30 is then further configured to supply each artificial example 52 of data to the extraction module 28, and in particular to its second extractor 62, for a new learning thereof, as represented by the arrow G'4.
- the retraining module 30 is configured to create each artificial example 52 of data by carrying out an inverse propagation of the random or pseudo-random vector through the component 20 considered which is a copy of the component 20 of the calculation module 18 which is to be trained again, as illustrated by the arrow G '1 in Figure 4; and if necessary through the second extractor 62 whose neural network or networks are then invertible, as illustrated by the arrow G'2 in FIG. 4, the second extractor 62 contained in the retraining module 30 being a copy of the second extractor 62 of the extraction module 28.
- the copy is performed each time before a new component 20 is added.
- the copy is performed before the component 20, and if necessary the second extractor 62, are trained with the data from the buffer memory 26.
- FIG. 5 representing a flowchart of the processing method according to the invention, the latter being implemented by the processing device 14.
- the processing device 14 acquires, via its acquisition module 16, the set of data to be processed, the latter being typically in the form of a data vector x.
- the acquisition module 16 optionally performs a normalization of the set of data(s) and/or an enrichment of the set of data(s), for example via one or multiple random angle rotations.
- the processing device 14 When, as an optional complement, the processing device 14 includes the extraction module 28, it extracts, during a next optional step 110 and via its extraction module 28, one or more characteristics common to several tasks in order to convert the set of data acquired in a simplified representation, which then makes it possible to then implement the part specific to each task more quickly, via the calculation module 18.
- This optional step 110 in fact corresponds to a task-agnostic step, which is implemented by the extraction module 28 and which corresponds to the part of the architecture of the processing device 14 which is agnostic to the tasks, as explained above.
- the processing device 14 calculates, during the following step 120 and via its calculation 18, a latent vector h k for each component 20 included in the calculation module 18 and from the set of data(s), that is to say either from data vector x acquired during the acquisition step 100 or from the simplified representation obtained at the end of the extraction step 110.
- each component 20 associated with a respective task and calculating the latent vector h k is configured to implement an invertible neural network, and this possibility of inverting the neural network of each component 20 then makes it possible to express the likelihood function of the input data easily as a function of the values of the latent space H, that is to say easily as a function of the latent vector h k , during the next step 130.
- the processing device 14 indeed determines, during step 130 and via its determination module 22, a task for each datum by evaluating the score likelihood for each component, this from the latent vector h k calculated for each component 20.
- the determined task is then that associated with the component 20 presenting the highest likelihood score, and the label t of the given task verifies for example equation (12) or even equation (13).
- the processing device 14 further comprises the feedback module 24, the processing device 14 performs during the next step 140 and via said feedback module 24, a storage in the buffer memory 26 of each unknown task datum, that is to say each datum for which the assessed likelihood score is inconsistent for the component associated with the assigned task, which is then considered as unknown.
- the feedback module 24 also triggers the creation of a new task if necessary, for example if the number of data stored in the buffer memory 26 is greater than the predefined number. If necessary, the calculation module 18 is preferably configured to then include a new component 20 associated with the new task, and the learning of the new component 20 is carried out from the data stored in the buffer memory 26, as described above.
- the processing device 14 optionally performs, during the next step 150, and via its calculation module 18 in reverse propagation according to the first embodiment of FIG. embodiment of FIG. 4, the creation of at least one artificial example 52 of data from the random or pseudo-random vector h s k generated by the determination module 22.
- the random or pseudo-random vector h s k is generated by the determination module 22 to correspond to the distribution of the latent space of the component C k which is to be trained again, and this vector h s k is then propagated in reverse from the latent space H towards the input space X via the invertible neural network of the component C k to be trained again in the example of figure 2, or alternatively via the invertible neural network of the copy of the component C k to be trained again which is included in the module d e retraining 30 in the example of FIG. 4.
- the artificial example, as well as its identifier, thus created are then supplied to the component C k of the calculation module 18 which is associated with the same identifier k.
- the processing device 14 also includes the extraction module 28, the latter then being composed of invertible neural networks, the random or pseudo-random vector h s k is also propagated through said extraction 28 in the opposite way, as shown in Figure 2 by the arrows G1 and G2.
- the retraining module 30 also includes a copy of said second extractor 62, the random or pseudo-random vector h s k is then propagated in an inverse manner also through the copy of said second extractor 62, then the artificial example 52 thus created by the retraining module 30 is then provided also to the second extractor 62 of the extraction module 28.
- the second extractor 62 is driveable, it is, like the component C k , driven again on the artificial example, by back-propagation of the gradient of the component Ck.
- the processing device 14 according to the invention then makes it possible to perform continuous learning based on generative neural networks, these neural networks also being invertible, which then makes it possible to express the likelihood function of the data of the input space X more easily depending on the values of the vectors of the latent space H.
- processing device 14 makes it possible to perform both unsupervised type learning and supervised type learning, as explained previously through the first, second, third and fourth applications described.
- Invertible networks also allow an exact calculation of the likelihood score of the data of the input space X according to the probabilistic distribution function of this input space, and to then determine if necessary if the likelihood score of a sample is inconsistent for the component associated with the assigned task, which then makes it possible to detect an unknown task in unsupervised learning.
- the use of invertible neural networks for each component 20 of the calculation module 18 makes it possible to use a single neural network at a time for the encoding from the input space X to latent space H and for decoding from said latent space H to said input space X, this decoding then making it possible to create artificial examples 52 for subsequent retraining of the neural networks of the components 20.
- the complementary aspect corresponding to the second embodiment of FIG. 4 where the processing device 14 also comprises the retraining module 30 distinct from the calculation module 18 then allows the generation of artificial examples 52 by the retraining module 30 in at the same time that the calculation module 18 continues to carry out the learning of tasks, which makes it possible to more easily and more regularly create artificial examples 52 for the subsequent retraining of the neural networks of the corresponding components 20.
- the invertible neural networks of the components 20 of the calculation module 18 and, where applicable, the invertible neural network of the second extractor 62 make it possible to implement the backpropagation algorithm. of the gradient with a lower amount of memory resources since the activations of each neuron can be reconstructed from the output of the corresponding network. This then makes it possible to recalculate the activations in parallel during the retro- propagation of the gradient, without having to save the activations of each neuron during an inference phase, and this reduced use of memory resources is then particularly suitable when the processing device 14 according to the invention is implemented in an embedded system. It is thus conceivable that the electronic processing device 14, and the associated processing method, according to the invention make it possible to offer a better solution to the phenomenon of catastrophic forgetting by better representing the tasks and then learning characteristics which are more discriminating. .
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Image Analysis (AREA)
- Information Transfer Systems (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR2007287A FR3112413B1 (fr) | 2020-07-09 | 2020-07-09 | Dispositif électronique et procédé de traitement de données à base de réseaux génératifs inversibles, système électronique de détection et programme d’ordinateur associés |
| PCT/EP2021/068861 WO2022008605A1 (fr) | 2020-07-09 | 2021-07-07 | Dispositif électronique et procédé de traitement de données à base de réseaux génératifs inversibles, système électronique de détection et programme d'ordinateur associés |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4179469A1 true EP4179469A1 (fr) | 2023-05-17 |
Family
ID=73497865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21742808.5A Pending EP4179469A1 (fr) | 2020-07-09 | 2021-07-07 | Dispositif électronique et procédé de traitement de données à base de réseaux génératifs inversibles, système électronique de détection et programme d'ordinateur associés |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20230252271A1 (fr) |
| EP (1) | EP4179469A1 (fr) |
| FR (1) | FR3112413B1 (fr) |
| WO (1) | WO2022008605A1 (fr) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12223951B2 (en) * | 2021-12-20 | 2025-02-11 | Adeia Guides Inc. | Methods and systems for responding to a natural language query |
| US12518112B2 (en) * | 2021-12-20 | 2026-01-06 | Adeia Guides Inc. | Methods and systems for responding to a natural language query |
| FR3138718B1 (fr) * | 2022-08-08 | 2024-10-04 | Commissariat Energie Atomique | Dispositif électronique et procédé de traitement de données comportant au moins un modèle d’intelligence artificielle auto-adaptatif avec apprentissage local, système électronique et programme d’ordinateur associés |
| CN116700208B (zh) * | 2023-05-25 | 2025-12-19 | 上海交通大学 | 一种基于可逆左流形的闭环系统故障诊断方法及系统 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018164435A1 (fr) * | 2017-03-08 | 2018-09-13 | Samsung Electronics Co., Ltd. | Appareil électronique, son procédé de commande, et support de stockage non transitoire lisible par ordinateur |
| US10791078B2 (en) * | 2017-07-30 | 2020-09-29 | Google Llc | Assistance during audio and video calls |
| US10771763B2 (en) * | 2018-11-27 | 2020-09-08 | At&T Intellectual Property I, L.P. | Volumetric video-based augmentation with user-generated content |
| US11031005B2 (en) * | 2018-12-17 | 2021-06-08 | Intel Corporation | Continuous topic detection and adaption in audio environments |
| US11763091B2 (en) * | 2020-02-25 | 2023-09-19 | Palo Alto Networks, Inc. | Automated content tagging with latent dirichlet allocation of contextual word embeddings |
-
2020
- 2020-07-09 FR FR2007287A patent/FR3112413B1/fr not_active Expired - Fee Related
-
2021
- 2021-07-07 US US18/004,640 patent/US20230252271A1/en active Pending
- 2021-07-07 EP EP21742808.5A patent/EP4179469A1/fr active Pending
- 2021-07-07 WO PCT/EP2021/068861 patent/WO2022008605A1/fr not_active Ceased
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022008605A1 (fr) | 2022-01-13 |
| FR3112413A1 (fr) | 2022-01-14 |
| FR3112413B1 (fr) | 2023-02-24 |
| US20230252271A1 (en) | 2023-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022008605A1 (fr) | Dispositif électronique et procédé de traitement de données à base de réseaux génératifs inversibles, système électronique de détection et programme d'ordinateur associés | |
| EP3707676B1 (fr) | Procédé d'estimation de pose d'une caméra dans le référentiel d'une scène tridimensionnelle, dispositif, système de réalite augmentée et programme d'ordinateur associé | |
| FR3118503A1 (fr) | Procédé et dispositif de détection d'anormalité de données | |
| FR2884008A1 (fr) | Systeme et procede de localisation de points d'interet dans une image d'objet mettant en oeuvre un reseau de neurones | |
| FR3088467A1 (fr) | Procede de classification d'une image d'entree representative d'un trait biometrique au moyen d'un reseau de neurones a convolution | |
| WO2022207573A1 (fr) | Autoencodeur multimodal a fusion de donnees latente amelioree | |
| FR3117223A1 (fr) | Système et procédé de contrôle de véhicule à base d’apprentissage machine | |
| EP3871153A1 (fr) | Retro-propagation d'erreurs sous forme impulsionnelle dans un reseau de neurones impulsionnels | |
| JP7205327B2 (ja) | 学習装置 | |
| FR3087033A1 (fr) | Procedes d'apprentissage de parametres d'un reseau de neurones a convolution et de detection d'elements d'interet visibles dans une image | |
| EP4632689A1 (fr) | Methode d'entrainement d'un modele d'apprentissage machine pour la decouverte d'objets dans une sequence d'images | |
| EP0681270A1 (fr) | Procédé de trajectographie d'objets et dispositif de mise en oeuvre de ce procédé | |
| FR3026526A1 (fr) | Procede et systeme de detection d'evenements de nature connue | |
| FR3129508A1 (fr) | Procédé d’apprentissage de valeurs de poids synaptique d’un réseau de neurones, procédé de traitement de données, programme d’ordinateur, calculateur et système de traitement associés | |
| WO2020157733A1 (fr) | Procédé dynamique d'imagerie tridimensionnelle | |
| EP4191530A1 (fr) | Procédé de localisation et cartographie simultanées intégrant un masquage temporel auto-supervisé et modèle d'apprentissage automatique pour générer un tel masquage | |
| FR3104291A1 (fr) | Procédé et système de configuration d’un dispositif d’imagerie d’un véhicule automobile comportant N capteurs et N réseaux de neurones encodeurs dédiés | |
| EP0447306A1 (fr) | Dispositif de reconnaissance de séquences dans un signal multidimensionnel | |
| FR3138718A1 (fr) | Dispositif électronique et procédé de traitement de données comportant au moins un modèle d’intelligence artificielle auto-adaptatif avec apprentissage local, système électronique et programme d’ordinateur associés | |
| FR3109002A1 (fr) | Dispositif et procédé pour le transfert de connaissance d’un réseau neuronal artificiel | |
| EP4150574B1 (fr) | Procédé de traitement d'images | |
| FR3146536A1 (fr) | Système de réseaux neuronaux par distillation, procédés d’entrainement améliorés | |
| EP4557166A1 (fr) | Procédé et dispositif de détermination d'appartenance aux données d'apprentissage utilisées pour l'entraînement d'un modèle de classification de données par apprentissage machine | |
| FR3152904A1 (fr) | Systèmes et procédés pour la détection séquentielle d’anomalies dans les réseaux IVN à l’aide d’une approche de l’espace d’état basée sur un graphe | |
| FR3134207A1 (fr) | Procédé et dispositif électronique de traitement de donnée(s) par réseau(x) de neurones avec résistance améliorée aux attaques adverses par approximation du gradient, programme d’ordinateur et système électronique de traitement d’objet(s) associés |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20230109 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: COMMISSARIAT A L'ENERGIE ATOMIQUE ET AUX ENERGIESALTERNATIVES |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |