论文信息 - A temporal neural system

A temporal neural system

Time is often the dominant information dimension. Applications for time-dependent adaptive systems include sequence generation and predication, image processing, and dynamic control. We have developed a temporal neural system which is composed of an architecture, processing nodes, and training algorithm. The architecture allows arbitrary connectivity between processing nodes including recurrent connections. The processing node includes higher order conjunctive terms, and the training algorithm allows arbitrarily configured topologies to be trained. We demonstrate the temporal neural system by simulating time series generation and a finite state machine.<<ETX>>

Lex A. Akers | Jay Heeb | L. Akers | J. Heeb

[1] C. Lee Giles,et al. Encoding Geometric Invariances in Higher-Order Neural Networks , 1987, NIPS.

[2] Colin Giles,et al. Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[3] Lex A. Akers,et al. An adaptive neural processing node , 1993, IEEE Trans. Neural Networks.

[4] J. M Brady. The theory of computer science: A programming approach , 1977 .

[5] I. Aleksander. The Theory of Computer Science , 1978 .

[6] DeLiang Wang,et al. Three neural models which process temporal information , 1988, Neural Networks.

[7] John J. Hopfield,et al. CONCENTRATION INFORMATION IN TIME: ANALOG NEURAL NETWORKS WITH APPLICATIONS TO SPEECH RECOGNITION PROBLEMS. , 1987 .

[8] C. Lee Giles,et al. Higher Order Recurrent Networks and Grammatical Inference , 1989, NIPS.

[9] Stephen Grossberg,et al. A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..