Discriminative learning in sequential pattern recognition
Citations
9,091 citations
3,120 citations
2,817 citations
Cites background or methods from "Discriminative learning in sequenti..."
...Here, it is useful to point out a connection between the above pretraining/fine-tuning strategy associated with hybrid deep networks and the highly popular minimum phone error (MPE) training technique for the HMM (see [147, 290] for an overview)....
[...]
...Many of the discriminative techniques for supervised learning in signal and information processing are shallow architectures such as HMMs [52, 127, 147, 186, 188, 290, 394, 418] and conditional random fields (CRFs) [151, 155, 281, 400, 429, 446]....
[...]
...Ideally, D should contain all possible documents, as in the maximum mutual information training for speech recognition where all possible negative candidates may be considered [147]....
[...]
...The framework described in [144] enables end-to-end performance optimization in the overall deep architecture using the unified learning framework initially published in [147]....
[...]
2,527 citations
1,948 citations
References
26,531 citations
13,190 citations
8,442 citations
"Discriminative learning in sequenti..." refers methods in this paper
...This posterior probability can be computed using an efficient forward-backward algorithm [50]....
[...]
...…comes from the fact that sentence tokens in the training set are independent of each other. γ i,r,s r (t ) is the occupation probability of state i at time t , given the label sequence s r and observation sequence X r , which can be obtained through an efficient forward-backward algorithm [50]....
[...]
6,831 citations