Evolving improved incremental learning schemes for neural network systems
作者： T. Seipone , J.A. Bullinaria
关键词:
摘要: It is well known that incremental learning can often be difficult for traditional neural network systems, due to newly learned information interfering with previously information. In this paper, we present simulation results which demonstrate how evolutionary computation techniques used generate learners exhibit improved performance over existing systems.
sci-hub.se 参考文章(16)
Robert M. French, Catastrophic interference in connectionist networks ,(2003)
Geoffrey E Hinton, David C Plaut, Using fast weights to deblur old memories conference cognitive science. pp. 177- 186 ,(1987)
Christophe Giraud-Carrier, A note on the utility of incremental learning Ai Communications. ,vol. 13, pp. 215- 223 ,(2000)
Christopher M. Bishop, Neural networks for pattern recognition ,(1995)
Michael McCloskey, Neal J. Cohen, Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem Psychology of Learning and Motivation. ,vol. 24, pp. 109- 165 ,(1989) , 10.1016/S0079-7421(08)60536-8
A.P. Engelbrecht, R. Brits, A clustering approach to incremental learning for feedforward neural networks international joint conference on neural network. ,vol. 3, pp. 2019- 2024 ,(2001) , 10.1109/IJCNN.2001.938474
Roger Ratcliff, Connectionist models of recognition memory: Constraints imposed by learning and forgetting functions. Psychological Review. ,vol. 97, pp. 285- 308 ,(1990) , 10.1037/0033-295X.97.2.285
John A. Bullinaria, Evolving efficient learning algorithms for binary mappings international joint conference on neural network. ,vol. 16, pp. 793- 800 ,(2003) , 10.1016/S0893-6080(03)00093-5
Marcus Frean, Anthony Robins, Catastrophic forgetting in simple networks: an analysis of the pseudorehearsal solution Network: Computation in Neural Systems. ,vol. 10, pp. 227- 236 ,(1999) , 10.1088/0954-898X_10_3_302
C. L. Blake, UCI Repository of machine learning databases www.ics.uci.edu/〜mlearn/MLRepository.html. ,(1998)