Learning Beyond Finite Memory in Recurrent Networks of Spiking Neurons

We investigate possibilities of inducing temporal structures without fading memory in recurrent networks of spiking neurons strictly operating in the pulse-coding regime. We extend the existing gradient-based algorithm for training feedforward spiking neuron networks, SpikeProp (Bohte, Kok, & La...

Full description

Saved in:
Bibliographic Details
Published in:Neural computation 2006-03, Vol.18 (3), p.591-613
Main Authors: Tiňo, Peter, Mills, Ashely J. S.
Format: Article
Language:English
Subjects:
Action Potentials - physiology
Algorithms
Animals
Applied sciences
Artificial Intelligence
Biological and medical sciences
Central Nervous System - physiology
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Fundamental and applied biological sciences. Psychology
General aspects
General aspects. Models. Methods
Humans
Learning
Learning - physiology
Learning and adaptive systems
Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects)
Memory
Memory - physiology
Nerve Net - physiology
Neural networks
Neural Networks (Computer)
Neural Pathways - physiology
Neurons
Neurons - physiology
Vertebrates: nervous system and sense organs
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We investigate possibilities of inducing temporal structures without fading memory in recurrent networks of spiking neurons strictly operating in the pulse-coding regime. We extend the existing gradient-based algorithm for training feedforward spiking neuron networks, SpikeProp (Bohte, Kok, & La Poutré, 2002), to recurrent network topologies, so that temporal dependencies in the input stream are taken into account. It is shown that temporal structures with unbounded input memory specified by simple Moore machines (MM) can be induced by recurrent spiking neuron networks (RSNN). The networks are able to discover pulse-coded representations of abstract information processing states coding potentially unbounded histories of processed inputs. We show that it is often possible to extract from trained RSNN the target MM by grouping together similar spike trains appearing in the recurrent layer. Even when the target MM was not perfectly induced in a RSNN, the extraction procedure was able to reveal weaknesses of the induced mechanism and the extent to which the target machine had been learned.
ISSN:0899-7667
1530-888X
DOI:10.1162/neco.2006.18.3.591