Evolving Spiking Networks with Variable Resistive Memories
This work addresses adaptive learning mechanisms for neuromorphic computing, which is incremental as it builds on existing spiking neuro-evolutionary systems by introducing variable resistive memories.
The paper tackled the problem of adaptive learning in neuromorphic computing by evolving spiking neural networks with variable resistive memories as synapses, and found that these networks outperformed static resistive memories and standard connections in a noisy robotic dynamic-reward scenario.
Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural networks. The evolutionary design process exploits parameter self-adaptation and allows the topology and synaptic weights to be evolved for each network in an autonomous manner. Variable resistive memories are the focus of this research; each synapse has its own conductance profile which modifies the plastic behaviour of the device and may be altered during evolution. These variable resistive networks are evaluated on a noisy robotic dynamic-reward scenario against two static resistive memories and a system containing standard connections only. Results indicate that the extra behavioural degrees of freedom available to the networks incorporating variable resistive memories enable them to outperform the comparative synapse types.