发明名称 |
HYBRID PRE-TRAINING OF DEEP BELIEF NETWORKS |
摘要 |
Pretraining for a DBN initializes weights of the DBN (Deep Belief Network) using a hybrid pre-training methodology. Hybrid pre-training employs generative component that allows the hybrid PT method to have better performance in WER (Word Error Rate) compared to the discriminative PT method. Hybrid pre-training learns weights which are more closely linked to the final objective function, allowing for a much larger batch size compared to generative PT, which allows for improvements in speed; and a larger batch size allows for parallelization of the gradient computation, speeding up training further. |
申请公布号 |
US2014164299(A1) |
申请公布日期 |
2014.06.12 |
申请号 |
US201213707088 |
申请日期 |
2012.12.06 |
申请人 |
Sainath Tara;Kingsbury Brian;Ramabhadran Bhuvana |
发明人 |
Sainath Tara;Kingsbury Brian;Ramabhadran Bhuvana |
分类号 |
G06N3/08 |
主分类号 |
G06N3/08 |
代理机构 |
|
代理人 |
|
主权项 |
1. In a deep belief network (DBN), a method for training the DBN for operational decoding comprising:
pre-training initial weights based on determined optimal weights; identifying, during pre-training, a batch size and number of parameters corresponding to the initial weights, the batch size larger than that allowable for purely generative pretraining; and invoking a plurality of machines for performing training in parallel fashion.
|
地址 |
Burlington MA US |