Adaptive Encoding Strongly Improves Function Approximation with CMAC

The Cerebellar Model Arithmetic Computer (CMAC) (Albus 1981) is well known as a good function approximator with local generalization abilities. Depending on the smoothness of the function to be approximated, the resolution as the smallest distinguishable part of the input domain plays a crucial role. If the binary quantizing functions in CMAC are dropped in favor of more general, continuous-valued functions, much better results in function approximation for smooth functions are obtained in shorter training time with less memory consumption. For functions with discontinuities, we obtain a further improvement by adapting the continuous encoding proposed in Eldracher and Geiger (1994) for difficult-to-approximate areas. Based on the already far better function approximation capability on continuous functions with a fixed topologically distributed encoding scheme in CMAC (Eldracher et al. 1994), we present the better results in learning a two-valued function with discontinuity using this adaptive topologically distributed encoding scheme in CMAC.

[1]  Helge Ritter,et al.  Neuronale Netze - eine Einführung in die Neuroinformatik selbstorganisierender Netzwerke , 1990 .

[2]  Derek A. Linkens,et al.  A fuzzified CMAC self-learning controller , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[3]  Alexander Staller,et al.  Function Approximation With Continuous-Valued ActivationFunctions in , 1994 .

[4]  Michael Hormel,et al.  A Self-organizing Associative Memory System for Control Applications , 1989, NIPS.

[5]  Martin Eldracher,et al.  Adaptive Topologically Distributed Encoding , 1994 .

[6]  James S. Albus,et al.  Brains, behavior, and robotics , 1981 .

[7]  P. C. Parks,et al.  Design Improvements in Associative Memories for Cerebellar Model Articulation Controllers (CMAC) , 1991 .

[8]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[9]  M. Eldracher.  A Topologically Distributed Encoding to Facilitate Learning , 1993 .

[10]  Walter Sebastian Mischo.  Receptive Fields for CMAC. An Efficient Approach , 1992 .

[11]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[12]  Hans Geiger,et al.  STORING AND PROCESSING INFORMATION IN CONNECTIONIST SYSTEMS , 1990 .

[13]  Wilfried Brauer,et al.  Classification of trajectories - Extracting invariants with a neural network , 1993, Neural Networks.

[14]  M. Thoma,et al.  Neurocontrol: Learning Control Systems Inspired by Neuronal Architectures and Human Problem Solving Strategies , 1992 .

[15]  Hyongsuk Kim,et al.  USE OF CMAC NEURAL NETWORKS IN REINFORCEMENT SELF-LEARNING CONTROL , 1991 .