Bidirectional continuous associator based on Gaussian potential function network

A bidirectional continuous associator (BCA) performing many-to-one forward association and one-to-many inverse association of an arbitrary continuous mapping is constructed on the basis of the multilayer Gaussian potential function network (GPFN). The constructed BCA represents a significant extension of the authors' previous work (1988), the multilayer feedforward potential function network, in which only the forward association of semicontinuous mapping with discrete output patterns is considered. The forward association of BCA uses a potential field synthesized over the domain of input space by a number of Gaussian potential function units (GPFUs). The synthesis is accomplished by learning the location, shape and necessary number of GPFUs. The inverse association of the BCA selects the desired input pattern that corresponds to the given output pattern and optimizes a certain performance index. This inverse association is carried out by an input pattern update. Such an inverse association has great potential for the implementation of a recall process and application to robotics.<<ETX>>

[1]  Sukhan Lee,et al.  Multilayer feedforward potential function network , 1988, IEEE 1988 International Conference on Neural Networks.

[2]  Kunihiko Fukushima,et al.  A neural network for visual pattern recognition , 1988, Computer.

[3]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[4]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[5]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[6]  B Kosko,et al.  Adaptive bidirectional associative memories. , 1987, Applied optics.

[7]  B. Kosko,et al.  Feedback stability and unsupervised learning , 1988, IEEE 1988 International Conference on Neural Networks.

[8]  M. Aizerman,et al.  Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning , 1964 .

[9]  J. Albus.  Mechanisms of planning and problem solving in the brain , 1979 .

[10]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.