Discrete symbolic optimization and Boltzmann sampling by continuous neural dynamics: Gradient Symbolic Computation
Computation and Language
2018-01-12 v1
Abstract
Gradient Symbolic Computation is proposed as a means of solving discrete global optimization problems using a neurally plausible continuous stochastic dynamical system. Gradient symbolic dynamics involves two free parameters that must be adjusted as a function of time to obtain the global maximizer at the end of the computation. We provide a summary of what is known about the GSC dynamics for special cases of settings of the parameters, and also establish that there is a schedule for the two parameters for which convergence to the correct answer occurs with high probability. These results put the empirical results already obtained for GSC on a sound theoretical footing.
Cite
@article{arxiv.1801.03562,
title = {Discrete symbolic optimization and Boltzmann sampling by continuous neural dynamics: Gradient Symbolic Computation},
author = {Paul Tupper and Paul Smolensky and Pyeong Whan Cho},
journal= {arXiv preprint arXiv:1801.03562},
year = {2018}
}