Recurrent neural network architecture with pre-synaptic inhibition for incremental learning

Authors:
Hiroyuki Ohta;Yukio Pegio Gunji
Affiliations:
Graduate School of Science and Technology, Kobe University, Rokkodai, Nada, Kobe, Japan;Department of Earth and Planetary Sciences, Faculty of Science, Kobe University, Nada, Kobe, Japan
Venue:
Neural Networks - 2006 Special issue: Neurobiology of decision making
Year:
2006

Citing 6
Cited 1

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Intelligence without representation

Artificial Intelligence
Gradient-based learning algorithms for recurrent networks and their computational complexity

Backpropagation
Reinforcement Learning

Reinforcement Learning
Self-Organizing Maps

Self-Organizing Maps
The spatiotemporal learning rule and its efficiency in separating spatiotemporal patterns

Biological Cybernetics

An incremental neural network with a reduced architecture

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a recurrent neural network architecture that is capable of incremental learning and test the performance of the network. In incremental learning, the consistency between the existing internal representation and a new sequence is unknown, so it is not appropriate to overwrite the existing internal representation on each new sequence. In the proposed model, the parallel pathways from input to output are preserved as possible, and the pathway which has emitted the wrong output is inhibited by the previously fired pathway. Accordingly, the network begins to try other pathways ad hoc. This modeling approach is based on the concept of the parallel pathways from input to output, instead of the view of the brain as the integration of the state spaces. We discuss the extension of this approach to building a model of the higher functions such as decision making.