Incremental learning of spatio-temporal patterns with model selection

Authors:
Koichiro Yamauchi;Masayoshi Sato
Affiliations:
Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, Japan;Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, Japan
Venue:
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Year:
2007

Citing 9
Cited 1

A sequential learning scheme for function approximation using minimal radial basis function neural networks

Neural Computation
Pruning using parameter and neuronal metrics

Neural Computation
A Modified General Regression Neural Network (MGRNN) with new, efficient training algorithms as a robust 'black box'-tool for data analysis

Neural Networks
Accurate on-line support vector regression

Neural Computation
Constructive Incremental Learning from Only Local Information

Neural Computation
Incremental Leaning and Model Selection for Radial Basis Function Network through Sleep

IEICE - Transactions on Information and Systems
Fast learning in networks of locally-tuned processing units

Neural Computation
Evolving fuzzy neural networks for supervised/unsupervised onlineknowledge-based learning

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Incremental learning methods with retrieving of interfered patterns

IEEE Transactions on Neural Networks

A decade of Kasabov's evolving connectionist systems: a review

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a biologically inspired incremental learning method for spatio-temporal patterns based on our recently reported "Incremental learning through sleep (ILS)" method. This method alternately repeats two learning phases: awake and sleep. During the awake phase, the system learns new spatio-temporal patterns by rote, whereas in the sleep phase, it rehearses the recorded new memories interleaved with old memories. The rehearsal process is essential for reconstructing the internal representation of the neural network so as not only to memorize the new patterns while keeping old memories but also to reduce redundant hidden units. By using this strategy, the neural network achieves high generalization ability. The most attractive property of the method is the incremental learning ability of non-independent distributed samples without catastrophic forgetting despite using a small amount of resources. We applied our method to an experiment on robot control signals, which vary depending on the context of the current situation.