论文信息 - Genetic evolution of neural networks that remember

Genetic evolution of neural networks that remember

The GENDALC system has been previously used to evolve NN topologies for natural language tasks. This paper presents results on additional tasks that require remembering and processing of previous input patterns. These results indicate that GENDALC is particularly well suited for tasks that require remembering.

J.J. Davila

[1] J. Elman. Distributed Representations, Simple Recurrent Networks, And Grammatical Structure , 1991 .

[2] David H. Wolpert,et al. No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[3] Sholom M. Weiss,et al. Computer Systems That Learn , 1990 .

[4] Casimir A. Kulikowski,et al. Computer Systems That Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning and Expert Systems , 1990 .

[5] Jaime Dávila. Genetic optimization of NN topologies for the task of natural language processing , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[6] D. Wolpert,et al. No Free Lunch Theorems for Search , 1995 .

[7] Michael I. Jordan. Attractor dynamics and parallelism in a connectionist sequential machine , 1990 .

[8] E. Spelke,et al. Origins of knowledge. , 1992, Psychological review.

[9] C. C. Goren,et al. Visual following and pattern discrimination of face-like stimuli by newborn infants. , 1975, Pediatrics.

[10] Giovanni Soda,et al. Local Feedback Multilayered Networks , 1992, Neural Computation.

[11] Richard D. Braatz,et al. On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[12] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.