EP4062329A1 - Verfahren zum bereitstellen eines erklärungsdatensatzes für ein ki-modul, computerlesbares speichermedium, vorrichtung und system - Google Patents
Verfahren zum bereitstellen eines erklärungsdatensatzes für ein ki-modul, computerlesbares speichermedium, vorrichtung und systemInfo
- Publication number
- EP4062329A1 EP4062329A1 EP20810956.1A EP20810956A EP4062329A1 EP 4062329 A1 EP4062329 A1 EP 4062329A1 EP 20810956 A EP20810956 A EP 20810956A EP 4062329 A1 EP4062329 A1 EP 4062329A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- data set
- module
- designed
- data record
- optimization
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000005457 optimization Methods 0.000 claims abstract description 72
- 238000004891 communication Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 2
- 208000000453 Skin Neoplasms Diseases 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 201000000849 skin cancer Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/045—Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Definitions
- the invention relates to a method for providing an explanation data set for an AI module, a computer-readable storage medium and a system.
- AI modules it is possible to carry out a classification or a regression for an input data set.
- an artificial neural network can be used to determine for each pixel of an image whether it shows skin cancer or not. It is also possible to use an AI module to determine whether the customer should receive a loan or not based on customer data of a customer of a bank.
- AI modules are complex data structures or programs that are trained for a task in a training phase or, in the case of reinforcement learning, during operation. For example, in an artificial neural network, the weights of a large number of In addition, further hyperparameters can be determined which determine the structure of the artificial neural network. The number of weights / parameters to be learned is very large.
- a problem with modern machine learning methods is that the complexity of the AI modules is great, so that it is difficult and in many cases impossible to explain in detail for humans why an AI module is based on an input data set for a certain output has arrived. In addition, it is difficult to explain why a certain input leads to an output and another input leads to the same or a different output.
- an AI module could be designed to assess whether a user should be granted a loan or not based on, among other things, the salary of a user. If the user is denied credit, he or she could demand an explanation for the negative decision.
- the above publication suggests the general idea of providing the user with an explanatory data record that contains alternative input data for the KI module that would have led to a positive decision in favor of the loan.
- the alternative explanatory record could indicate a higher income with which a positive credit decision would have been made by the AI module.
- an explanatory data record could contain information about which blood values would have to change in order to obtain a negative diagnosis regarding an illness.
- the explanatory dataset can also be used to derive behavioral measures that contribute to a healthier lifestyle.
- the object is achieved by a method according to claim 1, a computer-readable storage medium according to claim 14, a device according to claim 15 and by a system according to claim 17.
- the object is achieved in particular by a method for providing an explanatory data set for an AI module, comprising:
- a user data record which specifies at least one input data record of an KI module
- the KI module being designed to calculate an output data record for the input data record, e.g. by means of a regression and / or classification, the user data record comprising at least one target specification, which indicates a value of a data element in an output data set of the KI module;
- the AI module being designed to calculate an output data set for the explanatory data set that contains the information given by the target Data item includes;
- a core of the invention is that the task of finding an explanatory data set is modeled as an optimization task.
- a user can provide a target specification that can represent a desired result for the input data record after processing by the AI module.
- the target specification therefore specifies at least one value of a data element in an output data record of the KI module.
- the optimization task specifies a specific and a similarity metric, wherein minimizing the metrics can solve the optimization task in one embodiment.
- the specific and the similarity metric can each specify classes of metrics, so that a number of optimization tasks can be defined through a combination of different concrete specific and concrete similarity metrics, the solution of which provides different results in each case.
- the explanatory data set can provide a plurality of different explanations for the input data set.
- the user data record can comprise at least one boundary condition for the at least one optimization task, wherein the optimization method can calculate the at least one optimization task taking into account the at least one boundary condition of the user data record.
- the at least one boundary condition can include an approval specification, wherein an approval specification can specify the feature categories defined by the input data record in which the explanation data record may differ from the input data record.
- an approval specification can specify the feature categories defined by the input data record in which the explanation data record may differ from the input data record.
- the at least one boundary condition can include at least one weight, wherein a weight can indicate a preference for a change in a feature category of the input data record in the explanation data record.
- the at least one boundary condition can include at least one range specification, the at least one range specification being able to specify a permitted value range of a feature category of the explanation data record, in particular a maximum and / or minimum permitted deviation from a value in the input data record.
- the solution space for the at least one optimization task are restricted and the user only receives those solutions as explanatory data sets that are relevant to him.
- the explanatory data set can comprise a multiplicity of variations of the input data set, each of which fulfills the at least one boundary condition.
- the explanatory data set can comprise a large number of variations of the input data set, which can be generated by a combination of different metrics and optimization methods.
- the method can include receiving at least one provider data set, wherein the provider data set can include at least one constraint for the at least one optimization task, wherein the optimization method can calculate the at least one optimization task taking into account the at least one constraint of the provider data set.
- a provider data record with boundary conditions can thus also be received.
- certain boundary conditions can be specified by a user of an AI module and, on the other hand, by a provider or operator of an AI module.
- the user data set and the operator data set can be received separately as two different data units or as part of a single data set.
- the at least one boundary condition of the provider data record can indicate an output number, wherein the output number can indicate how many variations of the input data record are calculated and are included in the explanation data record.
- the number of variations can be limited.
- the number may be limited to the number of issues.
- the output number can indicate the number of optimization tasks to be solved multiplied by the number of optimization methods used.
- providing can of the explanation data set comprise a filtering, wherein the filtering can comprise a limitation of the solutions of the at least one optimization task specified by the explanation data set.
- the at least one optimization method can comprise a gradient method and / or a Newton method.
- a gradient method and a Newton method are efficient options that solve at least one optimization problem.
- the specific metric can be minimal if the target information matches the data element of the output data set of the KI module, wherein the specific metric can be in the form of cross entropy and / or mean square deviation, for example.
- the minimization of the specific metric thus ensures that the result data set leads to an output of the AI module that corresponds to the target specification.
- a cross entropy or a mean square deviation can be used as a specific metric. Both of these concrete metrics can be implemented efficiently and can be minimized by optimization methods.
- the similarity metric can be designed as an L p norm, in particular as an L °, L 1 and / or L 2 metric.
- the similarity metric ensures that the explanatory dataset is close to the input dataset.
- the use of a similarity metric and its mathematical optimization, i.e. minimization, through optimization methods has the advantage that a change vector is sparse or includes low values, for example the minimum number of changed vector values in the case of the L ° metric or the smallest possible root of the sum of the squared individual vector values in the case of the L 2 metric.
- the at least one optimization task can be specified by the formula mm M sp (5) + 2M in (5), where M sp is the specific
- Metric and M im can indicate the similarity metric and d can be selected from a set of permissible changes in the input data set.
- the amount of permissible changes to the input data record can be determined by at least one or the at least one boundary condition of the user data record and / or the provider data record.
- the method can include calculating an output data set using the KI module, wherein the explanation data set can be used as an input data set of the KI module.
- the method can thus also include the use of the calculated explanatory data set by the AI module. This can be used to check whether the explanation data record leads to the result indicated by the target specification.
- the object is also achieved in particular by a computer-readable storage medium which contains instructions which cause at least one processor to implement a method as described above when the instructions are executed by the at least one processor.
- a device for providing an explanatory data set comprising:
- a receiving unit which is designed to receive a user data set that specifies at least one input data set of an KI module, the KI module being designed to calculate an output data set for the input data set, for example by means of a regression and / or classification wherein the user data record comprises at least one target specification which specifies a value of a data element in an output data record of the KI module;
- An optimization unit which is designed to load an optimization task which specifies a specific metric and / or a similarity metric and which is also designed to include at least one solution of the at least one optimization task as an explanatory data set, taking into account the user data set and the AI module To calculate the use of at least one optimization method, the AI module being designed to calculate an output data record for the explanation data record, which includes the data element indicated by the target information;
- a provision unit which is designed to provide the explanation data set.
- the device can comprise an AI unit, which can be designed to calculate an output data set, wherein the explanation data set can be used as an input data set of the AI module.
- the receiving unit can be designed to receive at least one provider data set, wherein the provider data set can include at least one boundary condition for the at least one optimization task, wherein the optimization method can be configured to perform the at least one optimization task taking into account the at least one boundary condition of the provider data set to calculate.
- At least one server unit which in particular has a device as described above and a server communication unit;
- At least one client unit with a client communication unit which is designed to send a request to the server communication unit, in particular via a communication network; wherein the server communication unit is designed to provide an application-programmable interface designed to do so is to receive a user record and send an explanation record.
- FIG. 1 a schematic representation of a system
- FIG. 2 a schematic representation of the mode of operation of an AI module with an explanatory data set
- FIG. 3 a schematic representation of a device for providing an explanatory data set
- FIG. 4 a schematic representation of an optimization unit
- FIG. 5 an example of an input data record
- FIG. 6 an example of an explanatory data record
- FIG. 7 a schematic representation of a distributed system.
- FIG. 1 shows a schematic representation of a system 1 which determines an explanatory data set 2 for a user data set 20.
- the system 1 has a device 10 which is designed to determine the explanation data set 2 taking into account the user data set 20 and / or a provider data set 30.
- a device 10 can also be referred to as a counterfactory 10.
- the user data record 20 has an input data record 21.
- the input data set 21 comprises a multiplicity of data elements which form an input for an AI module 31.
- the input data set 21 can comprise image data, the data elements representing brightness values for pixels.
- the input data record 21 can include the characteristics of a bank customer, the data elements of the input data record 21 being able to indicate, for example, the income, the occupation and the age of the customer.
- the user data record 20 also has an approval information 22 which specifies the feature categories in which the explanation data record 2 may differ from the input data record 21.
- the approval information 22 can therefore also be viewed as a blacklist or whitelist.
- the user can specify, for example, that the feature “age” in the declaration data record 2 must not change since he has no influence on it.
- the approval information 22 can be specified as a vector, the number of dimensions of the vector corresponds to the number of feature categories of the input data record 21. Each data element of the vector can indicate whether a feature category may be changed.
- the user data record 20 includes at least one weight 23 which, in the exemplary embodiment shown, indicates a preference as to which feature categories in the explanatory data record 2 should preferably be changed or which not, without completely blocking them.
- the latter could indicate that a job change should be more likely in the explanation data record 2 than an increase in income.
- the user data record 20 comprises at least one area information 24 which specifies the areas in which the variation of a data element of the input data record 21 may move. This is useful when certain changes are not possible.
- the Range specification 24 ensures that a variation of brightness values is again a permissible brightness value, for example in the range from 0 to 255.
- the user data record 20 includes a target information 25 which indicates the desired result which is to be determined by the AI module 31.
- destination 25 could indicate a class.
- the target information 25 can indicate a specific value.
- the target information 25 can, for example, indicate that a loan is to be granted.
- the provider data set 30 has the AI module 31, which is designed to carry out a classification and / or regression.
- the AI module 31 can be a software component that is provided to the device 10.
- the AI module 31 can be made available as a library of an object-oriented programming language.
- the AI module 31 is made available via an application programmable interface (API).
- API application programmable interface
- the device 10 is provided with a description of the API as KI module 31.
- the KI module 31 can be any KI module.
- an AI module that is trained according to the principles of supervised learning and / or unsupervised learning.
- the AI module 31 can be an artificial neural network.
- any other implementation of an AI module is also conceivable, as long as it carries out a regression and / or classification for an input data set 21.
- the provider data record 30 also includes an approval information 32 which, like the approval information 22 of the user data record 20, has information about which feature categories may be changed.
- the provider of the AI module 31 can thus prevent changes in certain feature categories from being proposed as an explanation, such as a skin color, for example.
- the provider data record 30 has an output number 33, which indicates how many different explanations or variations of the Explanation data set 2 should include. This ensures that the user only receives a manageable number of explanations.
- the provider data record 30 includes a deviation information 34.
- the deviation information 34 indicates how much the explanation data record 2 must at least deviate from the input data record 21. For example, a statement that a loan would have been granted with a pay rise of a few cents could be very negative to a customer. It is thus possible to stipulate that a certain minimum change should be contained in the explanation data set 2.
- the approval information 22, the at least one weight 23, the range information 24, the target information 25, the approval information 32, the output number 33 and the deviation information 34 define boundary conditions that are taken into account by the device 10 when the explanation data set 2 is provided.
- FIG. 2 shows a schematic representation of the result of the processing of the explanation data set 2 by an AI module 31.
- FIG. 2 schematically shows that an explanation data set 2 provided by a device / counterfactory 10 is used as an input data set for an AI module 31 can be so that this determines an output data set 3.
- the output data set 3 specifies a data element 26 which can specify a regression result or a classification result.
- the data element 26 corresponds to the destination information 25.
- FIG. 3 shows a schematic detailed view of the device / counterfactory 10.
- the counterfactory 10 receives a user data set 20 and / or a provider data set 30 through a receiving unit 11.
- An optimization unit 12 is designed to use the user data set 20 and the provider data set 30 to generate an explanation data set 2 to be determined, which is provided by a provision unit 13.
- the mode of operation of the optimization unit 12 is shown in greater detail in FIG.
- the optimization unit 12 is designed to use a specific metric 14 and a similarity metric 15 to define an optimization task 16.
- This optimization task 16 is solved in the solver unit 18 using an optimization method 17 and the boundary conditions specified by the user data set 20 or provider data set 30, the solution being provided as explanatory data set 2.
- An optimization task 16 is given by the formula: min M sp (S) + lM ⁇ h (d, where M sp specifies the specific metric 14 and M im specifies the similarity metric 15 and d is selected from the set of permissible changes in the input data set 21.
- a large number of optimization tasks 16 can also be determined by choosing different specific metrics.
- the specific metric 14 can thus be designed as a cross entropy or as a mean square deviation.
- the similarity metric 15 can be designed as L °, L 1 or as L 2 norm.
- a first optimization task can, for example, use the cross entropy as the specific metric 14 and the L °, L 1 or L 2 norm as the similarity metric 15.
- a second optimization task can use the mean square deviation as the specific metric 14 and the L °, L 1 or L 2 norm as the similarity metric 15.
- FIGS. 5 and 6 show an example of an input data record 21 and an explanation data record 2 for a customer of a bank who would like to receive a loan.
- an AI module 31 determines that the customer will not receive any credit.
- the AI module 31 thus carries out a classification.
- the input data record 21 comprises the feature categories AGE 41, INCOME 41 'and PROFESSION 41 ".
- FIG. 6 shows an explanation data set 2 which is provided by the device / counterfactory 10.
- the device 10 is given a destination 25 as part of the user data record 20, so that the classification by the KI module 31 should show that a credit is granted by changing the data elements 42, 42 ', 42 ".
- the device / counterfactory 10 passed as approval information 22 that only the data elements of the feature categories INCOME 4 and OCCUPATION 41 "may be changed.
- Explanation data set 2 essentially corresponds to input data set 21. Only in feature category INCOME 4 is the value changed. With the explanation data set 2, the user thus receives a value for the income that is necessary in order to receive a classification by the KI module 31 with otherwise the same characteristics, so that the credit is granted.
- FIG. 7 shows a distributed system 4 which has a server 50 and a client 60.
- the server 50 and the client 60 can communicate over a communication network 70 such as the Internet.
- the client 60 has a client communication interface 63 which is communicatively connected to a client computing unit 62.
- the client 60 also has a client storage unit 61 which is designed to store an input data set 21.
- the server 50 has a server communication interface 53 which is communicatively connected to a server computing unit 52.
- the server computing unit 52 is designed to execute a program which the counter factory 10 implements.
- the functionality of the counter factory 10 is implemented by means of an API via the server
- Communication interface 53 provided. This means that the client 60 is designed to transmit a user data record 20 to the server 50 or the server communication interface 53 via an API call.
- the server 50 or the server computing unit 52 loads a provider data record 30 from a server storage unit 51. Additionally or alternatively, the server 50 can also receive the provider data record 30 from a second client via the server communication interface 53.
- the server computing unit 52 is also designed to determine an explanation data set 2, taking into account the user data set 20 and the provider data set 30, and to transmit this to the client 60 via the server communication interface 53.
- the server 50 executes the AI module 31 and to store the results, i.e. the respective output data sets 3.
- a user or a client 60 can then query an explanation data record 2 at a later point in time.
- a state of the KI module 31 used is also stored in the server memory unit 51 with the respective output data records 3, so that different versions of the KI module 31 can be tracked over time. It can be advantageous to save a flash value for the status of the AI module 31.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102019131639.1A DE102019131639B4 (de) | 2019-11-22 | 2019-11-22 | System zum Bereitstellen eines Erklärungsdatensatzes für ein KI-Modul |
PCT/EP2020/082749 WO2021099501A1 (de) | 2019-11-22 | 2020-11-19 | Verfahren zum bereitstellen eines erklärungsdatensatzes für ein ki-modul, computerlesbares speichermedium, vorrichtung und system |
Publications (1)
Publication Number | Publication Date |
---|---|
EP4062329A1 true EP4062329A1 (de) | 2022-09-28 |
Family
ID=73497788
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP20810956.1A Pending EP4062329A1 (de) | 2019-11-22 | 2020-11-19 | Verfahren zum bereitstellen eines erklärungsdatensatzes für ein ki-modul, computerlesbares speichermedium, vorrichtung und system |
Country Status (5)
Country | Link |
---|---|
US (1) | US20230025692A1 (de) |
EP (1) | EP4062329A1 (de) |
CN (1) | CN114830140A (de) |
DE (1) | DE102019131639B4 (de) |
WO (1) | WO2021099501A1 (de) |
-
2019
- 2019-11-22 DE DE102019131639.1A patent/DE102019131639B4/de active Active
-
2020
- 2020-11-19 WO PCT/EP2020/082749 patent/WO2021099501A1/de unknown
- 2020-11-19 EP EP20810956.1A patent/EP4062329A1/de active Pending
- 2020-11-19 US US17/778,724 patent/US20230025692A1/en active Pending
- 2020-11-19 CN CN202080080879.9A patent/CN114830140A/zh active Pending
Also Published As
Publication number | Publication date |
---|---|
CN114830140A (zh) | 2022-07-29 |
DE102019131639A1 (de) | 2021-05-27 |
DE102019131639B4 (de) | 2022-01-13 |
WO2021099501A1 (de) | 2021-05-27 |
US20230025692A1 (en) | 2023-01-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3785177B1 (de) | Verfahren und vorrichtung zum ermitteln einer netzkonfiguration eines neuronalen netzes | |
DE102005034160A1 (de) | Verfahren zur Optimierung der Durchführung von Messungen | |
DE102020206059A1 (de) | Computerimplementiertes Verfahren und System zum Trainieren eines Auswertungsalgorithmus, Computerprogramm und elektronisch lesbarer Datenträger | |
EP3931760A1 (de) | Training neuronaler netzwerke für effizientes implementieren auf hardware | |
WO2021099501A1 (de) | Verfahren zum bereitstellen eines erklärungsdatensatzes für ein ki-modul, computerlesbares speichermedium, vorrichtung und system | |
DE102019213061A1 (de) | Klassifizierung von KI-Modulen | |
DE102019127622B4 (de) | Abwehrgenerator, Verfahren zur Verhinderung eines Angriffs auf eine KI-Einheit und computerlesbares-Speichermedium | |
EP3748574A1 (de) | Adaptive bereinigung von messdaten um unterschiedliche arten von störungen | |
WO2020108748A1 (de) | System und verfahren zum auffinden von optimierten kombinationen von berechnungsfunktionen | |
DE102022203834A1 (de) | Verfahren zum Trainieren eines Algorithmus des maschinellen Lernens unter Berücksichtigung von wenigstens einer Ungleichheitsbedingung | |
DE102022207072A1 (de) | Verfahren zum Ermitteln einer optimalen Architektur eines künstlichen neuronalen Netzes | |
DE202022102072U1 (de) | Vorrichtung zum Trainieren eines Algorithmus des maschinellen Lernens unter Berücksichtigung von wenigstens einer Ungleichheitsbedingung | |
DE102022212902A1 (de) | Verfahren zum Trainieren eines künstlichen neuronalen Netzes | |
DE102016207768A1 (de) | Vorrichtung und Verfahren zum Bereitstellen einer Menge von Modultypen | |
DE102021207754A1 (de) | Erzeugung von computer-implementierten neuronalen netzwerken mit beseitigten architektonischen flaschenhälsen | |
DE102021109169A1 (de) | Verfahren zum Trainieren eines neuronalen Netzes | |
DE202022105588U1 (de) | Vorrichtung zum Trainieren eines Algorithmus des maschinellen Lernens durch ein bestärkendes Lernverfahren | |
DE102022132036A1 (de) | Computerimplementiertes Verfahren zur Konstruktion eines Bauteils | |
DE202021103700U1 (de) | Vorrichtung zum Erzeugen eines künstlichen neuronalen Netzes | |
WO2021180663A1 (de) | Mikroskopiesystem und verfahren zum verarbeiten von mikroskopbildern | |
DE102021205097A1 (de) | Computerimplementiertes Verfahren und System zur Bestimmung einer Kostenfunktion | |
DE102021207753A1 (de) | Effizientes beschneiden zweiter ordnung von computer-implementierten neuronalen netzwerken | |
DE102022004161A1 (de) | Verfahren zur Überwachung einer Anwendung durch ein Überwachungssystem sowie ein entsprechendes Überwachungssystem | |
DE102022110127A1 (de) | Assistenzsystem zur Generierung von Routenplänen für autonome landwirtschaftliche Arbeitsmaschinen | |
DE102022206892A1 (de) | Verfahren zum Bestimmen einer optimalen Architektur eines künstlichen neuronalen Netzes |
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: 20220621 |
|
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) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20231110 |