Evolution of Plastic Learning in Spiking Networks via Memristive Connections

Abstract

This article presents a spiking neuroevolutionary system which implements memristors as plastic connections, i.e. whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and variable topologies, allowing the number of neurons, connection weights, and inter-neural connectivity pattern to emerge. By comparing two phenomenological real-world memristor implementations with networks comprised of (i) linear resistors (ii) constant-valued connections, we demonstrate that this approach allows the evolution of networks of appropriate complexity to emerge whilst exploiting the memristive properties of the connections to reduce learning time. We extend this approach to allow for heterogeneous mixtures of memristors within the networks; our approach provides an in-depth analysis of network structure. Our networks are evaluated on simulated robotic navigation tasks; results demonstrate that memristive plasticity enables higher performance than constant-weighted connections in both static and dynamic reward scenarios, and that mixtures of memristive elements provide performance advantages when compared to homogeneous memristive networks.

Observation, Characterization and Modeling of Memristor Current Spikes

“…Memristor theory was first demonstrated in a model of the action of nerve axon membranes in 1976 [6], which was proposed as an alternative to the Hodgkin-Huxley circuit model) and this has led to the suggestion that they would be appropriate components for a computer built using a neuromorphic architecture [4]. Several simulations of neural nets containing memristors have been performed (see for example [7]). Recently, it was reported that circuits combining two memristors with two capacitors could produce self-initiating repeating phenomena similar in form to brain waves [8].…”

A study on emerging electronics for systems accepting soft errors

“…The output of each column can be sent to a amplifier that integrates and fires back to the corresponding row. A number of different implementations has been shown in [56,58,74,75]. …”

Skeleton-supported stochastic networks of organic memristive devices: Adaptations and learning

“…Recently, learning in the memristor-based networks is under a wide discussion. [25][26][27][28][29][30][31] We assumed that the training must result in the reinforcement of the conductivity in one branch (S-D1) and to inhibit it in the other one (S-D2)…”