Method and apparatus with neural network model training
AssigneesSamsung Electronics Co., Ltd., UIF (University Industry Foundation), Yonsei University
InventorsMinhyuk SEO, Hyunseo KOH, Jonghyun CHOI
Life of this patent
Estimating the term…
Abstract
A method and apparatus for training a neural network model are provided. The method of training a neural network model includes storing replay samples selected from among online stream samples in a replay buffer, selecting batch samples from the replay samples based on selection frequencies of the respective replay samples, determining a freeze layer group of the neural network model based on forward propagation of the neural network model using the batch samples, and training the neural network model based on backward propagation of layers not in the freeze layer group.
Claims20
A training method of training a neural network model performed by a computing device comprising storage hardware storing the neural network model and processing hardware, the training method comprising:
- storing replay samples selected from online stream samples in a replay buffer comprised in the storage hardware;
- selecting, by the processing hardware, batch samples from among the replay samples, the selecting based on selection frequencies of the respective replay samples;
- determining, by the processing hardware, a freeze layer group of the neural network model based on forward propagation of the neural network model using the batch samples;
- and
- training, by the processing hardware, the neural network model based on backward propagation of layers of the neural network model that are not in the freeze layer group.
An electronic device comprising:
- one or more processors;
- and
- a memory storing instructions configured to cause the one or more processors to:
- store, in a replay buffer in the memory, replay samples selected from online stream samples;
- select batch samples from the replay samples based on selection frequencies of the respective replay samples;
- determine a freeze layer group of the neural network model based on forward propagation of the neural network model using the batch samples;
- and
- train the neural network model based on backward propagation of layers not in the freeze layer group.
A method performed by a computing device, the method comprising:
- performing online training of a neural network with a stream of online training samples by:
- selecting replay samples, from among the online training samples, to be reused for training of the neural network model;
- maintaining usage statistics of the respective replay samples, including updating the usage statistic of each respective replay sample each time the replay sample is selected for reuse in training the neural network model;
- and
- based on the usage statistics, selecting, from among the replay samples, batch samples to be used for training the neural network, and updating the usage statistics of the selected replay samples based on the selection thereof as batch samples.
Dependencies are inferred from the claim text.