发明名称 |
SYSTEM AND METHOD FOR LOW-RANK MATRIX FACTORIZATION FOR DEEP BELIEF NETWORK TRAINING WITH HIGH-DIMENSIONAL OUTPUT TARGETS |
摘要 |
Systems and methods for reducing a number of training parameters in a deep belief network (DBN) are provided. A method for reducing a number of training parameters in a deep belief network (DBN) comprises determining a network architecture including a plurality of layers, using matrix factorization to represent a weight matrix of a final layer of the plurality of layers as a plurality of matrices, and training the DBN having the plurality of matrices. |
申请公布号 |
US2014019388(A1) |
申请公布日期 |
2014.01.16 |
申请号 |
US201313927192 |
申请日期 |
2013.06.26 |
申请人 |
INTERNATIONAL BUSINESS MACHINES CORPORATION |
发明人 |
KINGSBURY BRIAN E.D.;SAINATH TARA N.;SINDHWANI VIKAS |
分类号 |
G06N99/00 |
主分类号 |
G06N99/00 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|