发明名称 |
SYSTEMS AND METHODS FOR ACCELERATING HESSIAN-FREE OPTIMIZATION FOR DEEP NEURAL NETWORKS BY IMPLICIT PRECONDITIONING AND SAMPLING |
摘要 |
A method for training a deep neural network, comprises receiving and formatting speech data for the training, preconditioning a system of equations to be used for analyzing the speech data in connection with the training by using a non-fixed point quasi-Newton preconditioning scheme, and employing flexible Krylov subspace solvers in response to variations in the preconditioning scheme for different iterations of the training. |
申请公布号 |
US2015161987(A1) |
申请公布日期 |
2015.06.11 |
申请号 |
US201414500457 |
申请日期 |
2014.09.29 |
申请人 |
International Business Machines Corporation |
发明人 |
Horesh Lior;Kingsbury Brian E.D.;Sainath Tara N. |
分类号 |
G10L15/06;G10L15/16 |
主分类号 |
G10L15/06 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method for training a deep neural network, comprising:
receiving and formatting speech data for the training; preconditioning a system of equations to be used for analyzing the speech data in connection with the training by using a non-fixed point quasi-Newton preconditioning scheme; and employing flexible Krylov subspace solvers in response to variations in the preconditioning scheme for different iterations of the training; wherein the receiving, formatting, preconditioning and employing steps are performed by a computer system comprising a memory and at least one processor coupled to the memory. |
地址 |
Armonk NY US |