Image recognition, learning, and control in a cellular automata network
Raghu Raghavan · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1991
The theory of control is being widely used in optimization of dynamical systems. Learning algorithms in neural nets or in statistics have, however, seldom used the techniques of control. One reason for this is that the neural network parameters (synaptic weights) are used quasi- statically during processing after a learning phase, while control theory determines an optimal trajectory in time for the parameters. This issue is addressed in the context of a neural network dynamics introduced in previous publications as part of an image recognition system designed to integrate model-based and data-driven approaches in a connectionist framework. An important feature of this approach is that recognition must be achieved explicitly through the short- rather than the long-time behavior of the dynamics of the system. The dynamics arises naturally from requirements on the system which include incorporation of prior knowledge such as in inference rules, locality of inferences, and full parallelism. This system is also shown to be effective in image recognition. After reviewing the dynamical system, the authors compare new algorithms for learning the dynamics with Boltzmann-machine-like formulas. Interesting implications of this approach are pointed out, namely, that of a processing strategy that uses a dynamics for the weights as well as the states of the neurons. We conclude by mentioning the difficulties that remain with a control-theoretic strategy.© (1991) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.