520/600.776 Learning on Silicon
Johns Hopkins University

Projects

Spring 2002


Spike Timing-Dependent Plasticity in the Address Domain

Jacob Vogelstein, Francesco Tenore, Ralf Philipp, Miriam S. Adlerstein

NIPS*2002 paper and slides

Address-event representation (AER), originally proposed as a means to communicate sparse neural events between neuromorphic chips, has proven efficient in implementing large-scale networks with arbitrary, configurable synaptic connectivity. In this work, we further extend the functionality of AER to implement arbitrary, configurable synaptic plasticity in the address domain. As a proof of concept, we implement a biologically inspired form of spike timing-dependent plasticity (STDP) based on relative timing of events in an AER network. Experimental results from an analog VLSI integrate-and-fire network demonstrate address-domain learning on a task of grouping neurons with correlated inputs.