Adaptive Interaction and Its Application to Neural Networks

Abstract Adaptive interaction is a new approach to introduce adaptability into man-made systems. In this approach, a system is decomposed into interconnected subsystems that we call devices and adaptation occurs in the interactions. More precisely, interaction weights among these devices will be adapted in order to achieve the objective of minimizing a given cost function. The adaptation algorithm developed is mathematically equivalent to a gradient descent algorithm but requires only local information in its implementation. One particular application of adaptive interaction that we study in this paper is in neural networks. By applying adaptive interaction, we can achieve essentially the same adaptation as that using the well-known back-propagation algorithm but without the need of a feedback network to propagate the errors, which has many advantages in practice. A simulation is provided to show the effectiveness of our approach.

[1]  John J. Paulos,et al.  A neural network learning algorithm tailored for VLSI implementation , 1994, IEEE Trans. Neural Networks.

[2]  Kenneth L. Artis.  Design for a Brain , 1961 .

[3]  Francis Crick,et al.  The recent excitement about neural networks , 1989, Nature.

[4]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[5]  Feng Lin,et al.  Can supervised learning be achieved without explicit error back-propagation? , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[6]  R. D. Brandt,et al.  Self-tuning of PID controllers by adaptive interaction , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[7]  Alex Kacelnik.  Evolution and Learning, R.C. Bolies, M.D. Beecher (Eds.). Lawrence Erlbaum, Hillsdale, New Jersey (1988), x , 1990 .

[8]  José Luis Huertas,et al.  A CMOS analog adaptive BAM with on-chip learning and weight refreshing , 1993, IEEE Trans. Neural Networks.

[9]  R.V. Monopoli,et al.  Adaptive control: The model reference approach , 1981, Proceedings of the IEEE.

[10]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[11]  George C. Williams,et al.  Adaptation and Natural Selection , 2018 .

[12]  Feng Lin,et al.  Optimal layering of neurons , 1996, Proceedings of the 1996 IEEE International Symposium on Intelligent Control.

[13]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[14]  Torsten Lehmann,et al.  An analog CMOS chip set for neural networks with arbitrary topologies , 1993, IEEE Trans. Neural Networks.

[15]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[16]  B. C. Brookes,et al.  Information Sciences , 2020, Cognitive Skills You Need for the 21st Century.

[17]  Anuradha M. Annaswamy,et al.  Robust Adaptive Control , 1984, 1984 American Control Conference.

[18]  R. J. Williams,et al.  On the use of backpropagation in associative reinforcement learning , 1988, IEEE 1988 International Conference on Neural Networks.

[19]  Howard C. Card,et al.  Tolerance to analog hardware of on-chip learning in backpropagation networks , 1995, IEEE Trans. Neural Networks.

[20]  D. Luenberger.  Optimization by Vector Space Methods , 1968 .

[21]  Ludwig Braun,et al.  Adaptive control systems , 1959 .

[22]  Feng Lin,et al.  Supervised learning in neural networks without feedback network , 1996, Proceedings of the 1996 IEEE International Symposium on Intelligent Control.

[23]  Chung-Yu Wu,et al.  CMOS current-mode neural associative memory design with on-chip learning , 1996, IEEE Trans. Neural Networks.

[24]  Karl H. Pribram,et al.  Rethinking neural networks : quantum fields and biological data , 1993 .

[25]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.