Online training method, device and system and computer readable storage medium

Abstract

The invention relates to an online training method, device and system and a computer readable storage medium, and belongs to the field of deep learning. The method comprises the following steps: dividing all model parameters of a deep neural network model into a plurality of parts, and when real-time training sample data is obtained, training the deep neural network model by adopting model parameters corresponding to the real-time training data to obtain gradient information of each model parameter; Acquiring at least one target model parameter based on the gradient information of each model parameter and the model parameters corresponding to the real-time training data; And based on the at least one target model parameter and the gradient information of each model parameter, updating thedeep neural network model to achieve the purpose of on-line model training.

Description

technical field [0001] The present disclosure relates to the field of deep learning, and in particular to an online training method, device, system and computer-readable storage medium. Background technique [0002] With the development of science and technology, deep neural networks are widely used in model predictions. For example, in services such as search, advertising, and information flow, deep neural networks are used to train sample data to obtain predicted click-through rate estimates. Model. [0003] At present, the training method using deep neural network is mainly offline training. In this training method, the log used for training may be the operation log of the user some time ago, which makes the training samples lack real-time performance. Using the previous training sample data to train the model, The model can only be trained in offline mode, therefore, the model trained offline is not real-time. Contents of the invention [0004] In order to overcome t...

AI Technical Summary

Problems solved by technology

[0003] At present, the training method using deep neural network is mainly offline training. In this training method, the log used for training may be the operation log of the user some time ago, which makes the training samples lack real-time performance. Using the previous training sample data to train the model, The model can only be trained in offline mode, so the model trained offline is not real-time

Images