Journal
NEUROCOMPUTING
Volume 149, Issue -, Pages 435-442Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.neucom.2014.01.074
Keywords
Extreme learning machine; Event based processing; Synaptic kernel; Mixed domain processing; Spatio-temporal pattern recognition; Spatio-temporal receptive field
Categories
Ask authors/readers for more resources
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 spatiotemporal 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. (C) 2014 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available