Improving the separability of a reservoir facilitates learning transfer

Authors:
David Norton;Dan Ventura
Affiliations:
Computer Science Department, Brigham Young University, Provo, Utah;Computer Science Department, Brigham Young University, Provo, Utah
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 4
Cited 0

Learning to learn

Learning to learn
Isolated word recognition with the liquid state machine: a case study

Information Processing Letters - Special issue on applications of spiking neural networks
2007 Special Issue: An experimental unification of reservoir computing methods

Neural Networks
An analysis of noise in recurrent neural networks: convergence and generalization

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We use a type of reservoir computing called the liquid state machine (LSM) to explore learning transfer. The Liquid State Machine (LSM) is a neural network model that uses a reservoir of recurrent spiking neurons as a filter for a readout function. We develop a method of training the reservoir, or liquid, that is not driven by residual error. Instead, the liquid is evaluated based on its ability to separate different classes of input into different spatial patterns of neural activity. Using this method, we train liquids on two qualitatively different types of artificial problems. Resulting liquids are shown to substantially improve performance on either problem regardless of which problem was used to train the liquid, thus demonstrating a significant level of learning transfer.