Learning temporal clusters with synaptic facilitation and lateral inhibition

Authors:
Chris L. Baker;Aaron P. Shon;Rajesh P. N. Rao
Affiliations:
Department of Computer Science and Engineering, University of Washington, Box 352350, Seattle, WA 98195-2350, USA;Department of Computer Science and Engineering, University of Washington, Box 352350, Seattle, WA 98195-2350, USA;Department of Computer Science and Engineering, University of Washington, Box 352350, Seattle, WA 98195-2350, USA
Venue:
Neurocomputing
Year:
2005

Citing 6
Cited 0

Self-organizing maps

Self-organizing maps
Neural networks with dynamic synapses

Neural Computation
A view of the EM algorithm that justifies incremental, sparse, and other variants

Learning in graphical models
Temporal clustering with spiking neurons and dynamic synapses: towards technological applications

Neural Networks
Neural Systems as Nonlinear Filters

Neural Computation
A simplified gradient algorithm for iir synapse multilayer perceptrons

Neural Computation

Quantified Score

Hi-index	0.01

Visualization

Abstract

Short-term synaptic plasticity has been proposed as a way for cortical neurons to process temporal information. We present a model network that uses short-term plasticity to implement a temporal clustering algorithm. The model's facilitory synapses learn temporal signals drawn from mixtures of nonlinear processes. Units in the model correspond to populations of cortical pyramidal cells arranged in columns; each column consists of neurons with similar spatiotemporal receptive fields. Clustering is based on mutual inhibition similar to Kohonen's SOMs. A generalized expectation maximization (GEM) algorithm, guaranteed to increase model likelihood with each iteration, learns the synaptic parameters.