Evolving Unipolar Memristor Spiking Neural Networks
This work addresses the challenge of designing efficient neuromorphic hardware for robotics, though it is incremental as it builds on existing memristor research.
The paper tackled the problem of using unipolar memristor synapses, which switch between only two states, for neuromorphic computing by evolving network configurations with a self-adaptive process. The result showed that unipolar memristor networks evolved task-solving controllers faster than bipolar memristor networks and nonplastic networks while performing comparably on two robotics tasks.
Neuromorphic computing --- brainlike computing in hardware --- typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently citepd 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 non-Hebbian 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 a 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.