ELM Solutions for Event-Based Systems

TL;DR

This paper introduces modifications to Extreme Learning Machines (ELM) for processing event-based signals, enabling online spatio-temporal event detection with high accuracy, inspired by biological neural systems.

Contribution

The paper presents a novel approach to adapt ELMs for event-based systems by redefining hidden units as synaptic kernels, allowing effective online processing of spike-like signals.

Findings

Modified ELMs accurately detect spike events in real-time

The approach enables linear output solutions for event classification

Application to neural spike data demonstrates effectiveness

Abstract

Whilst most engineered systems use signals that are continuous in time, there is a domain of systems in which signals consist of events. Events, like Dirac delta functions, have no meaningful time duration. Many important real-world systems are intrinsically event-based, including the mammalian brain, in which the primary packets of data are spike events, or action potentials. In this domain, signal processing requires responses to spatio-temporal patterns of events. We show that some straightforward modifications to the standard ELM topology produce networks that are able to perform spatio-temporal event processing online with a high degree of accuracy. The modifications involve the re-definition of hidden layer units as synaptic kernels, in which the input delta functions are transformed into continuous-valued signals using a variety of impulse-response functions. This permits the use of linear solution methods in the output layer, which can produce events as output, if modeled as a classifier; the output classes are 'event' or 'no event'. We illustrate the method in application to a spike-processing problem.