Local Plasticity Rules for Desired Network-Level Behavior in Spiking Neural Networks

Identify the local synaptic and structural plasticity rules that yield a specified network-level behavior in spiking neural networks implemented on neuromorphic hardware, thereby linking local learning mechanisms to emergent system-level functionality.

Background

The paper discusses the need for on-device and online learning in neuromorphic systems, emphasizing local plasticity as a promising approach. However, due to emergent dynamics, deriving system-level behaviors from local rules remains challenging.

The authors explicitly state that it is not clear which local rules produce particular global behaviors, noting that evolutionary search and meta-learning have been used to rediscover useful rules but without establishing a general mapping from rules to behaviors.