A Pulse-Type Hardware Neuron Model with STDP for Brain-Like Information Processing System

K. Saeki, R. Shimizu, and Y. Sekine (Japan)

Keywords

STDP, brain-like information processing system, pulse type hardware neuron model, LTP/LTD, memory of temporal sequences and artificial neural network

Abstract

An artificial neural network that performs similarly to the human brain would be required to construct a brain-like information processing system. Especially, hardware models have been created that focus on how to have a learning function. Here, we focus on spike timing dependent synaptic plasticity (STDP) and construct a pulse-type hardware neuron model with STDP using analog VLSI technology. There are two types of STDP, one characterized by an asymmetric time window and the other by a symmetric time window (a Mexican hat type window). The literature reports that a Mexican-hat window participates in an inhibitory interneuron. In this study, we investigate the memory of temporal sequences using a pulse-type hardware neuron model (P-HNM) with STDP (a Mexican-hat time window). Specifically, we propose the construction of a P-HNM with STDP. In addition, we examine the temporal sequence patterns which were stored by using the P-HNM with STDP. As a result, we show that the P-HNM with STDP stores temporal sequence output voltage patterns in a way that conforms to the temporal sequence input current patterns.

Important Links:



Go Back


IASTED
Rotating Call For Paper Image