Search
Now showing items 1-5 of 5
Random Restarts in Global Optimization
(Georgia Institute of Technology, 2009-12-07)
In this article we study stochastic multistart methods for global optimization, which combine local search with random initialization, and their parallel implementations. It is shown that in a minimax sense the optimal ...
Separating the Vertices of N-Cubes by Hyperplanes and its Application to Artificial Neural Networks
(Georgia Institute of Technology, 1994-02)
We obtain a new sufficient condition that a region be classifiable by a 2-layer
feed-forward net using threshold activation functions. Briefly, it is either a convex
polytope, or that minus the removal of convex polytope ...
On the Inverse Fractal Problem for Two Dimensional Disjoint Polyhulled Attractors
(Georgia Institute of Technology, 1994-03)
Parallel Speed-Up of Monte Carlo Methods for Global Optimization
(Georgia Institute of Technology, 1990-08)
We introduce the notion of expected hitting time to a goal as a measure of the con-
vergence rate of a Monte Carlo optimization method. The techniques developed apply
to Simulated Annealing, Genetic Algorithms and other ...
Approximate Speedup by Independent Identical Processing
(Georgia Institute of Technology, 1994-05)
In this paper we prove that for algorithms which proceed to the
next state based on information available from the current state, identical independent parallel processing using stochastic multistart methods always yields ...