Evolving Unipolar Memristor Spiking Neural Networks

Abstract

Abstract-Neuromorphic computing -brainlike computing in hardware -typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently cited as strong synapse candidates due to their statefulness and potential for low-power implementations. To date, plentiful research has focused on the bipolar memristor synapse, which is capable of incremental weight alterations and can provide adaptive self-organisation under a Hebbian learning scheme. In this paper we consider the Unipolar memristor synapse -a device capable of nonHebbian switching between only two states (conductive and resistive) through application of a suitable input voltage -and discuss its suitability for neuromorphic systems. A self-adaptive evolutionary process is used to autonomously find highly fit network configurations. Experimentation on two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant nonplastic connections whilst performing at least comparably.

A Survey of Intelligent Chip Design Research Based on Spiking Neural Networks

“…In the process of a single spiking neuron firing a pulse in a spiking neural network, a spiking neuron receives input pulses from several dendrites and outputs axons from it. Many neurons form a network and learn systematically [22], as shown in figure 2. Five common spiking neuron models are the Hodgkin-Huxley (H-H) model [23 25], the leaky integrate and fire (LIF) model [ 26 28], and the Izhikevich model.…”