Kernel CMAC with Reduced Memory Complexity

Authors:
Gábor Horváth;Kristóf Gáti
Affiliations:
Department of Measurement and Information Systems, Budapest University of Technology and Economics, Budapest, Hungary H-1117;Department of Measurement and Information Systems, Budapest University of Technology and Economics, Budapest, Hungary H-1117
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Year:
2009

Citing 6
Cited 1

The interpolation capabilities of the binary CMAC

Neural Networks
Improving the Generalization Capability of the Binary CMAC

IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3 - Volume 3
Kernel CMAC With Improved Capability

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hardware implementation of CMAC neural network with reduced storage requirement

IEEE Transactions on Neural Networks
A self-organizing HCMAC neural-network classifier

IEEE Transactions on Neural Networks
Neighborhood sequential and random training techniques for CMAC

IEEE Transactions on Neural Networks

Using CMAC for mobile robot motion control

ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part II

Quantified Score

Hi-index	0.01

Visualization

Abstract

Cerebellar Model Articulation Controller (CMAC) has some attractive features: fast learning capability and the possibility of efficient digital hardware implementation. Besides these attractive features it has a serious drawback: its memory complexity may be very large. In multidimensional case this may be so large that practically it cannot be implemented. To reduce memory complexity several different approaches were suggested so far. Although these approaches may greatly reduce memory complexity we have to pay a price for this complexity reduction. Either both modelling and generalization capabilities are deteriorated, or the training process will be much more complicated. This paper proposes a new approach of complexity reduction, where properly constructed hash-coding is combined with regularized kernel representation. The proposed version exploits the benefits of kernel representation and the complexity reduction effect of hash-coding, while smoothing regularization helps to reduce the performance degradation.