SYSTEMS AND METHODS FOR COMBINING STOCHASTIC AVERAGE GRADIENT AND HESSIAN-FREE OPTIMIZATION FOR SEQUENCE TRAINING OF DEEP NEURAL NETWORKS

• Main Authors: DOGNIN PIERRE, GOEL VAIBHAVA
• Format: Patent
• Language: English
• Published: 29.10.2015
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

A method for training a deep neural network (DNN), comprises receiving and formatting speech data for the training, performing Hessian-free sequence training (HFST) on a first subset of a plurality of subsets of the speech data, and iteratively performing the HFST on successive subsets of the plural...