TWiki> CSTR Web>Listen>ListenTerm2201415 (revision 8)EditAttach

2014-15Term 2
12.01.15
SLT review and planning meeting
19.01.15
A large-scale CTC-trained RNN system + review of sequence-to-sequence learning (Steve)
26.01.15
Regression-base CD modelling of DNNs (Peter)
02.02.15

Review of speedup techniques

Noise Contrastive Estimation, Neural Network Joint models for MT and Variance regularization of RNNLM (Siva)

09.02.15
An Algorithm for Training Polynomial Networks (there's also an interesting but tangential video presentation) (Gustav)
16.02.15
No meeting due to Andrew Senior's visit
23.02.15
Acoustic modelling from SLT (joint effort)
02.03.15
Sum-product networks (Liang)
09.03.15
Text-dependent speaker verification, phoneme background model for IB-based diarization, i-Vector diarization with PLDA scoring (Mark and Mike)
16.03.15
"Intriguing properties of neural networks" and "On the number of linear response regions of deep neural networks" (Pawel and Gustav)
23.03.15
Bilingual RNNs and other LM papers from SLT (Siva)
TBC
A Convolutional Neural Network for Modelling Sentences and Multilingual Models for Compositional Distributional Semantics by Phil Blunsom and co from Oxford (Steve)
Edit | Attach | Print version | History: r10 < r9 < r8 < r7 < r6 | Backlinks | Raw View | Raw edit | More topic actions...
Topic revision: r8 - 10 Feb 2015 - 18:59:56 - Main.pbell1
 
This site is powered by the TWiki collaboration platformCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback
This Wiki uses Cookies