A deep learning system and a model parameter adjustment method

Abstract

The invention relates to a deep learning system and a model parameter adjustment method. The system comprises a right brain-like module which is a right brain-like neural network with a global featurememory function; The left brain-like module is a left brain-like neural network with a local area feature response function; The similarity filtering module is used for filtering the output result ofthe right brain-like module by calculating the similarity between the output result of the right brain-like module and the local regional data, n output results with the highest similarity are reserved, n is a natural number larger than 1, and the output of the similarity filtering module serves as the input of the left brain-like module; And the game equalization module is used for carrying outparameter adjustment on the right brain-like module and the left brain-like module in a game mode including maximum and minimum so as to achieve game equalization of the input of the right brain-likemodule and the output of the left brain-like module. The contradiction between the global features and the local features can be solved.

Description

[0001] This application claims the priority of the Chinese patent application submitted to the China Patent Office on December 19, 2017, the application number is 201711378502.8, and the application name is "a deep learning system and network data processing method based on brain-like games", all of which The contents are incorporated by reference in this application. technical field [0002] The invention belongs to the fields of data processing, network security and artificial intelligence, and specifically relates to a deep learning system and a method for adjusting model parameters. Background technique [0003] With the increasing scale of the Internet, a large number of new types of network attack methods have emerged. Facing the current situation that the danger of network attacks is increasing and network security problems are becoming more and more severe, traditional network defense technologies have been difficult to meet the needs of network security. In order to...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the above-mentioned problems existing in the existing deep learning system, the present invention provides a deep learning system and a model parameter adjustment method to solve the contradiction between the global feature and the local feature, and realize the integration of the global Intelligent real-time network data processing of and local features, this method is not only applicable to the error back propagation training method of the deep learning system, but also suitable for the non-error back propagation training method of the deep learning system

Images