Spiking neural network analog circuit based on reinforcement learning

Abstract

The invention belongs to the technical field of spiking neural networks, and discloses a spiking neural network analog circuit based on reinforcement learning. The spiking neural network analog circuit comprises an input layer nerve cell, a hidden layer nerve cell, an output nerve cell and a synapse; the input layer neurons are connected with the hidden layer neurons through synapses, and the hidden layer neurons are connected with the output neurons through the synapses; and the synapse is used for adjusting the first pulse signal of the pre-stage neuron according to the weight value and thentransmitting the adjusted first pulse signal to the post-stage neuron, and is also used for receiving the second pulse signal output by the post-stage neuron and updating the weight value according to the time difference between the first pulse signal and the second pulse signal and the reward signal. Based on reinforcement learning, a pulse neural network circuit is built, and an XOR classification function is achieved. Compared with a traditional pulse neural network, the method has the advantages of higher training speed and higher accuracy.

Description

technical field [0001] The invention belongs to the technical field of pulse neural network, and more specifically relates to a pulse neural network circuit based on reinforcement learning. Background technique [0002] Looking back at the history of AI, we will find that it is closely related to biological neural networks. However, although the traditional artificial neural network was born out of the biological neural network, there is a huge difference in the internal mechanism of the two. The gap between biological neural networks. There are indications that in order to make great progress in AI and computer technology, human beings must jump out of the shackles of the von Neumann architecture and existing machine learning algorithms, and turn to explore the mysteries of the brain and build a new type of brain-like computer. Therefore, brain-inspired computing or neuromorphic computing (neuromorphic computing) based on Spiking Neural Network (SNN) has received more and...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the defects of the prior art, the purpose of the present invention is to provide a pulse neural network circuit based on reinforcement learning, which aims to solve the problem of slow training speed and low precision in the prior art due to the unsatisfactory execution of complex tasks by the pulse neural network autonomously. question

Images