Synthesis of neural networks for spatio-temporal spike pattern recognition and processing

TL;DR

This paper introduces a fast, flexible method for synthesizing neural networks that process time-encoded signals, enabling efficient recognition of sparse spike-based information like speech.

Contribution

It presents a novel synthesis approach for neural networks that handle time-encoded signals with sparse neurons, allowing customizable neuronal parameters and rapid optimization.

Findings

Effective recognition of speech from spike time encoding

Sparse neural network implementation with customizable parameters

Fast optimization process for network synthesis

Abstract

The advent of large scale neural computational platforms has highlighted the lack of algorithms for synthesis of neural structures to perform predefined cognitive tasks. The Neural Engineering Framework offers one such synthesis, but it is most effective for a spike rate representation of neural information, and it requires a large number of neurons to implement simple functions. We describe a neural network synthesis method that generates synaptic connectivity for neurons which process time-encoded neural signals, and which makes very sparse use of neurons. The method allows the user to specify, arbitrarily, neuronal characteristics such as axonal and dendritic delays, and synaptic transfer functions, and then solves for the optimal input-output relationship using computed dendritic weights. The method may be used for batch or online learning and has an extremely fast optimization process. We demonstrate its use in generating a network to recognize speech which is sparsely encoded as spike times.