A memristor-based adaptive neuron circuit

Abstract

The present invention provides an adaptive neuron circuit based on a memristor, comprising: a charging circuit composed of an excitation pulse, a nonvolatile memristor and a capacitor; a discharge circuit composed of a volatile memristor, a capacitor and a resistor; The voltage signal at the terminal is used as the output pulse of the neuron circuit; the working process is as follows: after the non-volatile memristor receives the excitation pulse, the capacitor is charged through the charging circuit, and the capacitor voltage gradually increases. When the voltage at both ends of the volatile memristor When it is less than the threshold voltage, the output pulse is 0. When the voltage across the volatile memristor is greater than or equal to the threshold voltage, the capacitor is discharged through the discharge circuit, and the voltage across the resistor is used as the output pulse to generate an action potential; under the action of the excitation pulse , the resistance value of the non-volatile memristor gradually increases, resulting in the generated action potential frequency becoming smaller and smaller, simulating the characteristic that neurons gradually adapt to constant external stimuli. The invention simulates the adaptive function of neurons.

Description

technical field [0001] The invention belongs to the field of brain-like bionics, and more specifically relates to an adaptive neuron circuit based on a memristor. Background technique [0002] Simulating the physiological structure and working mechanism of the human brain to construct a bionic neural computing system is an important way to realize artificial intelligence. The human brain is composed of about 10 billion neurons and about 10 billion synapses, in which a single neuron is interconnected with multiple protrusions to form a complex network structure. Therefore, the premise of simulating the structure of the human brain is that the hardware implements neurons and synapses. There are two basic units of the synapse. Traditional artificial neurons and artificial synapses are constructed based on CMOS circuits. Dozens or even hundreds of transistors are often required to realize a single neuron or synapse. The circuit structure is complicated, the area is large, and t...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to provide a memristor-based adaptive neuron circuit, which aims to solve the problem that the prior art cannot simulate the ability of neurons to adapt to constant stimulation

Images