发明名称 |
METHOD FOR TRAINING A LEARNING MACHINE HAVING A DEEP MULTI-LAYERED NETWORK WITH LABELED AND UNLABELED TRAINING DATA |
摘要 |
<p>A method for training a learning machine having a deep network with a plurality of layers, includes applying a regularizer to one or more of the layers of the deep network; training the regularizer with unlabeled data; and training the deep network with labeled data. Also, an apparatus for use in discriminative classification and regression, including an input device for inputting unlabeled and labeled data associated with a phenomenon of interest; a processor; and a memory communicating with the processor. The memory includes instructions executable by the processor for implementing a learning machine having a deep network structure and training the learning machine by applying a regularizer to one or more of the layers of the deep network; training the regularizer with unlabeled data; and training the deep network with labeled data.</p> |
申请公布号 |
WO2009100417(A3) |
申请公布日期 |
2009.11.05 |
申请号 |
WO2009US33532 |
申请日期 |
2009.02.09 |
申请人 |
NEC LABORATORIES AMERICA, INC. |
发明人 |
WESTON, JASON;COLLOBERT, RONAN |
分类号 |
G06F15/18;G06F9/44 |
主分类号 |
G06F15/18 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|