Issue No. 02 - February (1986 vol. 8)
Mandayam A. L. Thathachar , Department of Electrical Engineering, Indian Institute of Science, Bangalore 560012, India.
P. S. Sastry , Department of Electrical Engineering, Indian Institute of Science, Bangalore 560012, India.
Relaxation labeling processes are a class of mechanisms that solve the problem of assigning labels to objects in a manner that is consistent with respect to some domain-specific constraints. We reformulate this using the model of a team of learning automata interacting with an environment or a high-level critic that gives noisy responses as to the consistency of a tentative labeling selected by the automata. This results in an iterative linear algorithm that is itself probabilistic. Using an explicit definition of consistency we give a complete analysis of this probabilistic relaxation process using weak convergence results for stochastic algorithms. Our model can accommodate a range of uncertainties in the compatibility functions. We prove a local convergence result and show that the point of convergence depends both on the initial labeling and the constraints. The algorithm is implementable in a highly parallel fashion.
M. A. Thathachar and P. S. Sastry, "Relaxation Labeling with Learning Automata," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 8, no. , pp. 256-268, 1986.