A Sensitive Long Short-Term Memory Method Based on State Change Differentiation

Abstract

The invention discloses a sensitive long-term and short-term memory method based on state change differentiation. In order to improve the traditional LSTM neural network's ability to respond to short-term information, a neural unit of the long-term and short-term memory network with increased information sensitivity is added, which can It greatly increases its ability to respond to short-term information, improves the real-time performance of its application, and enables more complete real-time analysis, further analysis of micro-actions and other contents, and improves the application value.

Description

technical field

[0001] The invention relates to the field of long-term and short-term memory networks, in particular to a sensitive long-term and short-term memory method based on state change differentiation. Background technique

[0002] Artificial intelligence is one of the three important disciplines in the 21st century, and it is an important support for national science, economy and people's livelihood. Among them, long short-term memory network (LSTM) is an important algorithm for memory-based recognition, which has been recognized in many aspects including semantics, actions, texts, etc., and has good value.

[0003] The existing long-term and short-term memory network still has a major problem, that is, it adopts the method of long-term and short-term memory to improve the analysis ability of information in the long-term sequence of the entire video, but it does not respond to short-term information at all. This makes the existing long and short-term memory network...

Images