Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Small sample online training method and device and storage medium

A training method and small sample technology, applied in neural learning methods, neural architectures, biological neural network models, etc., can solve the problem of difficult to carry mobile devices and embedded platforms, limited storage, power consumption and computing power, and complex computing. Training parameters and other issues to achieve the effect of solving catastrophic forgetting, portability and energy efficiency, and high training accuracy

Pending Publication Date: 2022-06-24
昆山市工业技术研究院有限责任公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] First of all, the current mainstream optimization algorithms have complex calculations and a large number of training parameters, which are limited by storage, power consumption and computing power, and are difficult to carry on mobile devices and embedded platforms.
Secondly, in practical application scenarios, it is often difficult to collect more samples, and too little data will have a negative impact on model training. For example, because a small amount of training data is difficult to provide enough information for the model to learn, the model may not be able to converge ;The model learns completely irrelevant information of the training data, which makes the model overfit the training data; it is easy to fall into the local optimal value, etc.
Again, in the process of continuous online training of new samples, it will cause catastrophic forgetting of old samples

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Small sample online training method and device and storage medium
  • Small sample online training method and device and storage medium
  • Small sample online training method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] This embodiment proposes a small sample online training method, and the method is implemented through the following technical solutions:

[0051] By using the CIFAR100 data set to train the VGG16 neural network, the weight parameters are obtained, and the weight parameters are used as the original training parameters of the pre-training model;

[0052] Collect and mark samples in actual application scenarios. It should be noted that the specified preset amount of collected samples batch_size=32, and when the specified preset amount of collected samples batch_size=32, input training is performed on the samples;

[0053] Input the labeled samples and original training parameters into the pre-training model for several training iterations to update the original training parameters;

[0054]The pre-training model is obtained based on the online training neural network. The online training neural network includes convolutional layer, interval batch normalization module, RELU...

Embodiment 2

[0110] A small sample online training device provided by an embodiment of the present invention includes a memory and a processor;

[0111] the storage medium is used to store instructions;

[0112] The processor is configured to operate in accordance with the instructions to perform the steps of the following methods:

[0113] The neural network is trained through the data set to obtain the weight parameters, and the weight parameters are used as the original training parameters of the pre-training model;

[0114] Collect and label a specified preset amount of samples;

[0115] The labeled samples and original training parameters are input into the pre-trained model for several training iterations to update the original training parameters.

Embodiment 3

[0117] The computer-readable storage medium provided by the embodiment of the present invention stores a computer program on it, and when the program is executed by a processor, implements the steps of the following method:

[0118] The neural network is trained through the data set to obtain the weight parameters, and the weight parameters are used as the original training parameters of the pre-training model;

[0119] Collect and label a specified preset amount of samples;

[0120] The labeled samples and original training parameters are input into the pre-trained model for several training iterations to update the original training parameters.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a small sample online training method and device and a storage medium, and belongs to the technical field of calculation, reckoning or counting. The method comprises the following steps: training a neural network through a data set to obtain a weight parameter, and taking the weight parameter as an original training parameter of a pre-training model; collecting and marking a specified preset quantity of samples; and inputting the marked samples and the original training parameters into a pre-training model for training so as to update the original training parameters. The pre-training model is adopted to train and update original training parameters, the problems that in the prior art, an optimization algorithm is limited by influences of storage, power consumption and computing power and is difficult to be carried on mobile equipment and an embedded platform for use, and a small number of samples are prone to causing overfitting are solved, and meanwhile, in the process of online training of new samples, the optimization efficiency is greatly improved. And disastrous forgetting of old samples can be caused.

Description

technical field [0001] The invention relates to a small sample online training method, device and storage medium, belonging to the technical field of calculation, calculation or counting. Background technique [0002] In recent years, deep neural networks have achieved unprecedented success in speech recognition, image recognition and medical applications, among which convolutional neural networks have a wide range of applications in the field of visual recognition, such as handwritten digit recognition, character recognition, face detection, Cross-media search, face recognition, facial expression analysis, car detection. For the parameter optimization process of neural network training, different learning algorithms have been proposed to train neural networks, among which the gradient-based algorithm, that is, the gradient descent algorithm, is the most used. However, realizing online training of deep neural networks on hardware has always been a difficult problem for rese...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/084G06N3/047G06N3/045
Inventor 王汉霖疏建梁天柱
Owner 昆山市工业技术研究院有限责任公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products