Recurrent neural network generates a basis for sensory image cancellation

Authors:
Patrick D. Roberts
Affiliations:
Neurological Sciences Institute, Oregon Health Sciences University, 505 NW, 185th Avenue, Portland, OR 97209, USA
Venue:
Neurocomputing
Year:
2005

Citing 1
Cited 2

Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation

2009 Special Issue: The first second: Models of short-term memory traces in the brain

Neural Networks
Model of auditory prediction in the dorsal cochlear nucleus via spike-timing dependent plasticity

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

This study investigates the temporal dynamics of recurrent layers and their relevance to storage of temporal information. A recurrent layer is shown to generate a dynamical basis that allows cancellation of predictable sensory images via and adaptive mechanism based on spike-timing dependent plasticity.