CN108921281A - A kind of field adaptation method based on depth network and countermeasure techniques - Google Patents
A kind of field adaptation method based on depth network and countermeasure techniques Download PDFInfo
- Publication number
- CN108921281A CN108921281A CN201810429822.XA CN201810429822A CN108921281A CN 108921281 A CN108921281 A CN 108921281A CN 201810429822 A CN201810429822 A CN 201810429822A CN 108921281 A CN108921281 A CN 108921281A
- Authority
- CN
- China
- Prior art keywords
- network
- training
- algorithm
- field
- confrontation
- 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; CALCULATING OR 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; CALCULATING OR 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
A kind of field adaptation method based on depth network and countermeasure techniques of the present invention is related to deep learning, transfer learning, field adaptation, convolutional neural networks, the technologies such as confrontation network.We increase by two confrontation subnets on the basis of finely tuning Alexnet, and for the difference between the amendment different field sample of confrontation type, arriving in high-level layers of study can sharing feature.The cost of handmarking in big data environment can be effectively reduced in the method, there is certain practical significance.The algorithm proposes innovation on the basis of new target risk upper error, and algorithm mainly includes initial phase and network training stage.In initial phase, according to new upper error and new neuronal layers are constructed, while increasing corresponding loss and regularization term, and initial work is carried out to network and data set.Training stage replaces original hyper parameter by probability threshold value, runs several iteration cycles according to the SGD algorithm of probability iteration, until meeting condition, training terminates.Final trained network can effectively substitute handmarking's process, obtain more, more accurate marked sample.
Description
Technical field
A kind of field adaptation algorithm based on depth network and countermeasure techniques of the present invention, algorithm are related to including that convolution is refreshing
Through network, deep learning, machine learning optimization, belong to artificial intelligence field.In particular to the new error based on the derivation of equation
Previous increase multiple-branching construction and loss function finely tune the good AlexNet of pre-training after fighting in subnet, are related to out one
The new combination of kind fights network, field adaptation (transfer learning) task in artificial intelligence can be effectively completed, in different necks
Expressing for knowledge migration is carried out between domain.
Background technique
Data set offset is can not be ignored the problem of in machine learning field.Data set is description real world object
The one-sided of body is stated, and the mutually isostructural model of training on the data set for describing the same collection of objects, generalization ability is often
There are deviation, effect is not ideal enough.Data set offset reduces generalization ability of the model on same type objects.For true
For the world, data set offset can be understood as model and overfitting problem have occurred on data set.Domain adaptation is attempted to solve number
According to collection offset problem, model is improved in target domain data based on similitude, the otherness between source domain and target domain
Performance.The development of deep learning is so that profound learning model also implies that needs are big with the parameter for more needing to learn
The sample training model of amount.On the other hand, searching out quantity, enough to have the training of exemplar bolster model be extremely difficult
's.
Summary of the invention
To solve the above-mentioned problems, a kind of field adaptation method based on depth network and countermeasure techniques of the present invention, not only
The offset problem between FIELD Data can be effectively corrected, and may learn the representation space of neck inter-domain sharing, algorithm
It can be adapted for unsupervised field adaptation task, i.e. target domain needs not exist for any label and can run.The present invention
Field adaptation method can save a large amount of manpower markers work, for solving the problems, such as under big data that flag data is rare
There is wide applicability.
A kind of field adaptation method based on depth network and countermeasure techniques of the present invention, mainly includes the following steps that:
Step 1:Obtain the sample of source domain and the sample of label and target domain.Source domain and target domain difference
Be derived from two approximate fields, wherein the sample of source domain has a label, and the sample of target domain does not have a label, two fields it
Between to have certain similitude, i.e., the knowledge that can be multiplexed can be acquired between field.
Step 2:Adaptation network is constructed, it is random initial using the good parameter initialization AlexNet of ImageNet pre-training
Change network others parameter.The purpose of algorithm is that a proper subspace is established between field, the feature in this proper subspace
It can be shared by two fields.AlexNet is a kind of depth convolutional network, we construct this neck using depth network
Domain knowledge is indicated, while being lost by increasing confrontation come the difference degree between amendment field.The communication process of loss passes through anti-
It is realized to gradient descent method.
Step 3:According to task, network correlation hyper parameter, such as learning rate, probability threshold value, dropout rate etc. are initialized.Net
Network hyper parameter needs manually determine that the convergence and performance to algorithm have important influence.In general, the learning rate of algorithm can
To give the value of a very little, make network convergence using more frequently batch gradient decline, probability threshold value is poor according to specific field
Off course degree determines, dropout rate then over-fitting in order to prevent.
Step 4:Using the alternate gradient back-propagation algorithm such as SGD training network parameter of probability, training terminates to obtain most
Final cast and result.The alternate gradient back-propagation algorithm of probability can be by hyper parameter " probability threshold value " it controls in very little
In range, so that hyper parameter is easier to search for.Training generallys use several periods, each period, we were traversed using SGD
Primary all data samples.After a few cycles, depth network training is completed, and algorithm terminates.
The present invention has the advantages that and effect:
1) it is proposed that new aiming field upper error establishes new network structure for domain based on new upper error
Adaptation, model are made of two son confrontation networks, have stronger confrontation dynamics and public characteristic ability to express.
2) compared to the balance that hyper parameter is used to control loss, we have proposed a kind of more flexible replacement methods, greatly
Amplitude reduce hyper parameter search and control it is difficult, it is easier to the different degrees of distributional difference of adaptation.
3) our algorithm obtains performance best at present on the domain adaptation data collection of some classics.
Detailed description of the invention
Fig. 1 is a kind of schematic network structure of the field adaptation method based on depth network and countermeasure techniques of the present invention.
Fig. 2 is a kind of algorithm flow schematic diagram of the field adaptation method based on depth network and countermeasure techniques of the present invention.
Specific embodiment
A kind of realization of the field adaptation method based on depth network and countermeasure techniques of the present invention is by initial phase, instruction
Practice stage and service stage composition.Initial phase includes data initialization and model initialization, and the training stage includes several times
Gradient back-propagation process, according to the size of data set, the number of iterations is differed from several hundred times to tens of thousands of times, until the number of iterations
Meet a certain condition or network convergence, then training is completed.
Initial phase:
Step 1, data initialization.The input of network is a tensor, usually has the color image of RGB triple channel,
Firstly, for all pictures, we pass through grayscale image the tensor of its size scaling to 227 × 227 × 3 simple
Image is repeated 3 times, cromogram is become.Secondly, R, G, B three-dimensional need to subtract the mean value of data set first, then divided by standard
Difference, so that data meet standard and are just distributed very much, this operation is also referred to as z-score standardization.Such data prediction makes
Network parameter is easier to restrain when must training.
Step 2, model initialization:
Model initialization is first loaded into the good parameter of the i.e. related pre-training of AlexNet, secondly, increasing some layers and correspondence
Loss, regularization term, structure as shown in Figure 1 initializes, just every layer parameter except the original layer of AlexNet
It is 0 that beginning, which turns to and obeys mean value, and the truncation that standard deviation is 1 just too distribution random numbers are set to when initializing for offset parameter
0。
Training stage:
Step 1, the training of network:
Training method is based on following formula:Enabling H is the hypothesis collection space that VC-dimension is d, and m have label sample
Originally from DSMiddle sampling obtains, m' unlabeled exemplars respectively fromWithMiddle sampling obtains, for all η ∈ H at least with
Probability 1- δ inequality
We try to optimize following target:
Wherein hyper parameter λ > 0, β > 0 controls the influence that two confrontation subnets accordingly lose item.
We need learning parameter θ={ θc,θl,θm}.We disassemble out 3 loss functions that two are fought subnet
Come, and replaces optimization process with following training objective in an iteration:
Wherein p1,p2∈ [0,1] is probability threshold value, for controlling the training of each loss function in iteration, in net
When network starts to train, probability threshold value is provided, each time before iteration, one 0 to 1 random number is generated, if random number is arrived 0
p1Between, then select LMAs the loss function of current iteration, similarly, if random number is in p1And p2Between, selectionMake
For the target of current iteration, if random number is in p2To between 1, L is selectedCAs loss function.
Step 2, the termination of network:
The termination when reaching any one following condition of the training process of network:
1) setting value maxIter indicates that maximum number of iterations is trained if training process reaches maximum number of iterations
It terminates.
2) before network reaches maxIter the number of iterations, given threshold lossChangeThreshold, if continuously
The loss absolute value of the difference of network is less than lossChangeThreshold twice, then it is assumed that network parameter has been restrained, training
It terminates.
According to above-mentioned initialization and training operation, network will converge to the sufficiently low point of loss, in this point
Solution be exactly the final solution of model, finally, training complete network can be used for predicting the unmarked sample of target domain, generation
For manually with higher accuracy rate label unknown data.
Claims (7)
1. a kind of field adaptation method based on depth network and countermeasure techniques of the present invention, in the use pair of depth convolutional neural networks
Damage-retardation is become estranged distributional difference between parallel organization diminution field.
2. the algorithm mainly includes three phases:Network structure construction, confrontation loss function construction, parallelization backpropagation.
3. network have it is multiple input and multiple outputs, synonym training in complete one have monitor task and one it is unsupervised
Task.
4. hyper parameter needs best to achieve the effect that by fine adjustment in input phase.
5. SGD algorithm is had modified in the training process of network, can be in an iteration, use is kind with random number
The multiple loss functions of probability alternating gradient descent algorithm training of son, the current best loss of selection each time carry out the instruction of network
Practice.
6. network can jump back and forth between different loss functions according to the selection of probability value.
7. network is end-to-end depth adaptation network, parallelization confrontation loss migrates knowledge between field.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810429822.XA CN108921281A (en) | 2018-05-08 | 2018-05-08 | A kind of field adaptation method based on depth network and countermeasure techniques |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810429822.XA CN108921281A (en) | 2018-05-08 | 2018-05-08 | A kind of field adaptation method based on depth network and countermeasure techniques |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108921281A true CN108921281A (en) | 2018-11-30 |
Family
ID=64404123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810429822.XA Pending CN108921281A (en) | 2018-05-08 | 2018-05-08 | A kind of field adaptation method based on depth network and countermeasure techniques |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108921281A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135579A (en) * | 2019-04-08 | 2019-08-16 | 上海交通大学 | Unsupervised field adaptive method, system and medium based on confrontation study |
CN110489661A (en) * | 2019-07-24 | 2019-11-22 | 武汉大学 | A kind of social networks prediction technique based on generation confrontation network and transfer learning |
CN111278085A (en) * | 2020-02-24 | 2020-06-12 | 北京百度网讯科技有限公司 | Method and device for acquiring target network |
CN112016451A (en) * | 2020-08-27 | 2020-12-01 | 贵州师范大学 | Training sample labeling cost reduction method for transfer learning |
CN112989702A (en) * | 2021-03-25 | 2021-06-18 | 河北工业大学 | Self-learning method for equipment performance analysis and prediction |
-
2018
- 2018-05-08 CN CN201810429822.XA patent/CN108921281A/en active Pending
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135579A (en) * | 2019-04-08 | 2019-08-16 | 上海交通大学 | Unsupervised field adaptive method, system and medium based on confrontation study |
CN110489661A (en) * | 2019-07-24 | 2019-11-22 | 武汉大学 | A kind of social networks prediction technique based on generation confrontation network and transfer learning |
CN111278085A (en) * | 2020-02-24 | 2020-06-12 | 北京百度网讯科技有限公司 | Method and device for acquiring target network |
CN111278085B (en) * | 2020-02-24 | 2023-08-29 | 北京百度网讯科技有限公司 | Method and device for acquiring target network |
CN112016451A (en) * | 2020-08-27 | 2020-12-01 | 贵州师范大学 | Training sample labeling cost reduction method for transfer learning |
CN112989702A (en) * | 2021-03-25 | 2021-06-18 | 河北工业大学 | Self-learning method for equipment performance analysis and prediction |
CN112989702B (en) * | 2021-03-25 | 2022-08-02 | 河北工业大学 | Self-learning method for equipment performance analysis and prediction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108921281A (en) | A kind of field adaptation method based on depth network and countermeasure techniques | |
Li | Deep reinforcement learning | |
CN109635917B (en) | Multi-agent cooperation decision and training method | |
CN109992670B (en) | Atlas completion method based on knowledge atlas neighborhood structure | |
Valdez et al. | Modular neural networks architecture optimization with a new nature inspired method using a fuzzy combination of particle swarm optimization and genetic algorithms | |
CN113361680B (en) | Neural network architecture searching method, device, equipment and medium | |
US10262274B2 (en) | Incremental learner via an adaptive mixture of weak learners distributed on a non-rigid binary tree | |
CN116523079A (en) | Reinforced learning-based federal learning optimization method and system | |
CN110443372A (en) | A kind of transfer learning method and system based on entropy minimization | |
CN108009635A (en) | A kind of depth convolutional calculation model for supporting incremental update | |
WO2024114121A1 (en) | Method for constructing intelligent computation engine of artificial intelligence cross-platform model on basis of knowledge self-evolution | |
CN114819091B (en) | Multi-task network model training method and system based on self-adaptive task weight | |
CN115907001A (en) | Knowledge distillation-based federal diagram learning method and automatic driving method | |
CN115495771A (en) | Data privacy protection method and system based on self-adaptive adjustment weight | |
CN117994635B (en) | Federal element learning image recognition method and system with enhanced noise robustness | |
CN110490324A (en) | A kind of gradient decline width learning system implementation method | |
Castellon et al. | Federated learning with incremental clustering for heterogeneous data | |
CN110569985A (en) | Online heterogeneous transfer learning method based on online and offline decision-making integrated learning | |
CN112364980B (en) | Deep neural network training method based on reinforcement learning under weak supervision scene | |
CN113505210A (en) | Medical question-answer generating system based on lightweight Actor-Critic generating type confrontation network | |
Wani et al. | Training supervised deep learning networks | |
Jamil et al. | Model selection in online learning for times series forecasting | |
CN110489435A (en) | Data processing method, device and electronic equipment based on artificial intelligence | |
CN116776950A (en) | Lifelong learning method based on sample replay and knowledge distillation | |
Yan et al. | A double weighted naive bayes for multi-label classification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181130 |
|
WD01 | Invention patent application deemed withdrawn after publication |