Search International and National Patent Collections

1. (WO2018196676) NON-CONVEX OPTIMIZATION BY GRADIENT-ACCELERATED SIMULATED ANNEALING

Pub. No.:    WO/2018/196676    International Application No.:    PCT/CN2018/083749
Publication Date: Fri Nov 02 00:59:59 CET 2018 International Filing Date: Fri Apr 20 01:59:59 CEST 2018
IPC: G06N 3/04
Applicants: HUAWEI TECHNOLOGIES CO., LTD.
Inventors: HO, Chiu Man
Title: NON-CONVEX OPTIMIZATION BY GRADIENT-ACCELERATED SIMULATED ANNEALING
Abstract:
A computer-implemented method of training a neural network comprises: identifying, by one or more processors, a set of parameters for a cost function for the neural network; applying, by the one or more processors, a gradient optimization of the cost function to generate a set of intermediate optimized parameter values for the cost function; initializing, by the one or more processors, a simulated annealing optimization of the cost function using the set of intermediate optimized parameter values for the cost function; applying, by the one or more processors, the simulated annealing optimization of the cost function to generate a set of final optimized parameter values for the cost function; assigning, by the one or more processors, the set of final optimized parameter values as weights for connections of the neural network; and using, by the one or more processors, the neural network to perform operations.