Paper Info
Title
Discrete symbolic optimization and Boltzmann sampling by continuous neural dynamics: Gradient Symbolic Computation.
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.
Year
Venue
Field
2018
arXiv: Computation and Language
Convergence (routing),Symbolic dynamics,Applied mathematics,Computer science,Symbolic computation,Sampling (statistics),Artificial intelligence,Boltzmann constant,Dynamical system,Machine learning,Computation,Free parameter
DocType
Volume
Citations 
Journal
abs/1801.03562
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Paul Tupper100.68
Paul Smolensky221593.76
Pyeong Whan Cho300.34