For a network of spiking neurons that encodes information in the timing of individual spike-times, we derive a supervised learning rule, emph{SpikeProp, akin to traditional error-backpropagation and show how to overcome the discontinuities introduced by thresholding. With this algorithm, we demonstrate how networks of spiking neurons with biologically reasonable action potentials can perform complex non-linear classification in fast temporal coding just as well as rate-coded networks. We perform experiments for the classical XOR-problem, when posed in a temporal setting, as well as for a number of other benchmark datasets. Comparing the (implicit) number of spiking neurons required for the encoding of the interpolated XOR problem, it is demonstrated that temporal coding requires significantly less neurons than instantaneous rate-coding.

Other Architecture Styles (acm C.1.3), Models of Computation (acm F.1.1), Learning (acm I.2.6), Models (acm I.5.1)
Neural nets (msc 82C32), Learning and adaptive systems (msc 68T05), Pattern recognition, speech recognition (msc 68T10), Knowledge representation (msc 68T30), Neural networks, artificial life and related topics (msc 92B20)
Software (theme 1), Logistics (theme 3), Energy (theme 4)
Software Engineering [SEN]
Intelligent and autonomous systems

Bohte, S.M, La Poutré, J.A, & Kok, J.N. (2000). Error-backpropagation in temporally encoded networks of spiking neurons. Software Engineering [SEN]. CWI.