Concept of LIF Neuron Circuit for Rate Coding in Spike Neural Networks
Andrei Velichko, П. П. Борисков
Abstract
This brief presents a concept of leaky integrate-and-fire neuron (LIF) based on oscillator circuit for a spike neural network with firing rate coding. The circuit contains a switching element with an S-shaped current-voltage characteristic and two capacitors; a control resistor shunts one of the capacitors. The circuit is characterized by a strong dependence of the frequency of relaxation oscillations on the magnitude of the control resistor. The dependence has a sigmoid-like form, and we present an analytical method for dependence calculation. The circuit provides theoretical perspectives for the pairing of resistive sensors with a neural network and for creating neuromorphic devices with artificial intelligence.