“2016”版本间的差异
来自cslt Wiki
（→Visualization） |
（→DNN architecture） |
||
| 第8行： | 第8行： | ||
* [http://t.cn/RfZHxko MICRO 2016 ] | * [http://t.cn/RfZHxko MICRO 2016 ] | ||
* [[媒体文件:Cambricon-X.pdf| Cambricon-X: An Accelerator for Sparse Neural Networks]] | * [[媒体文件:Cambricon-X.pdf| Cambricon-X: An Accelerator for Sparse Neural Networks]] | ||
| + | * [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/2/26/REVISE_SATURATED_ACTIVATION_FUNCTIONS.pdf revise saturated activation functions] | ||
==Visualization== | ==Visualization== | ||
2016年12月1日 (四) 08:17的最后版本
DNN architecture
- Ying Zhang et al. Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
- ICLR2017: OUTRAGEOUSLY LARGE NEURAL NETWORKS: THE SPARSELY-GATED MIXTURE-OF-EXPERTS LAYER
- lightRNN from microsoft
- Kaiming He et al. Deep Residual Learning for Image Recognition
- Wei-Ning Hsu et al. Exploiting Depth and Highway Connections in Convolutional Recurrent Deep Neural Networks for Speech Recognition
- MICRO 2016
- Cambricon-X: An Accelerator for Sparse Neural Networks
- revise saturated activation functions
Visualization
- Visualizing and Understanding Genomic Sequences Using Deep Neural Networks
- On the Role of Nonlinear Transformations in Deep Neural Network Acoustic Models
- Understanding_intermediate_layers_using_linear_classifier_probes
Speaker recognition
- INTERSPEECH 2016 Fri-O-2-2 :Special Session: The RedDots Challenge: Towards Characterizing Speakers from Short Utterances
- INTERSPEECH 2016 Fri-O-3-2 : Special Session: The Speakers in the Wild (SITW) Speaker Recognition Challenge
