Title :
Silicon synapses self-correct for both mismatch and design inhomogeneities
Author :
Bamford, S.A. ; Murray, A.F. ; Willshaw, D.J.
Author_Institution :
Neuroinf. Doctoral Training Centre, Univ. of Edinburgh, Edinburgh, UK
Abstract :
A neuromorphic chip with an array of neurons has connections (`synapses`) which implement a biological learning mechanism known as spike-timing-dependent plasticity. STDP is a homeostatic mechanism which regulates the firing rate of neurons. In this reported work, this mechanism is shown to reduce variation in performance between neurons, due to both mismatch in fabrication and inhomogeneities in the electronic design.
Keywords :
medical computing; neural nets; neurophysiology; prosthetic power supplies; STDP; biological learning mechanism; design inhomogeneity; electronic design; homeostatic mechanism; mismatch inhomogeneity; neural prosthetic device; neuromorphic chip; neuron array; neuron firing rate regulation; spike-timing-dependent plasticity;
Journal_Title :
Electronics Letters
DOI :
10.1049/el.2012.0257