A framework to deal with interference in connectionist systems

Authors:
Vicente Ruiz de Angulo;Carme Torras
Affiliations:
Institut de Robòtica i Informàtica Industrial, (CSIC‐UPC), Edifici NEXUS, Gran Capità 2‐4, 08034‐Barcelona, Spain E‐mail: {ruiz,torras}@iri.upc. ...;-
Venue:
AI Communications
Year:
2000

Citing 8
Cited 3

Neural network design and the complexity of learning

Neural network design and the complexity of learning
Training a 3-node neural network is NP-complete

COLT '88 Proceedings of the first annual workshop on Computational learning theory
Optimal brain damage

Advances in neural information processing systems 2
Generalization by weight-elimination with application to forecasting

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Locally Weighted Learning

Artificial Intelligence Review - Special issue on lazy learning
Minimally Disturbing Learning

IWANN '91 Proceedings of the International Workshop on Artificial Neural Networks
The effects of adding noise during backpropagation training on a generalization performance

Neural Computation
On-line learning with minimal degradation in feedforward networks

IEEE Transactions on Neural Networks

Neural computing increases robot adaptivity

Natural Computing: an international journal
Sequential Learning in Feedforward Networks: Proactive and Retroactive Interference Minimization

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Natural inspiration for artificial adaptivity: some neurocomputing experiences in robotics

UC'05 Proceedings of the 4th international conference on Unconventional Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We analyze the conditions under which a memory system is prone to interference between new and old items. Essentially, these are the distributedness of the representation and the lack of retraining. Both are, however, desirable features providing compactness and speed. Thus, a two‐stage framework to palliate interference in this type of systems is proposed based on exploiting the information available at each moment. The two stages are separated by the instant at which a new item becomes known: (a) interference prevention, prior to that instant, consists in preparing the system to minimize the impact of learning new items and (b) retroactive interference minimization, posterior to that instant, seeks to learn the new item while minimizing the damages inflicted on the old items. The subproblems addressed at the two stages are stated rigorously and possible methods to solve each of them are presented.