大数据智能-论文阅读
阅读论文清单
基础
Understanding the difficulty of training deep feedforward neural networks.
数据集
ImageNet: A Large-Scale Hierarchical Image Database, CVPR 2009.
ImageNet Classification with Deep Convolutional Neural Networks, NIPS 2012.
机器视觉基础
DeepFace: Closing the Gap to Human-Level Performance in Face Verification, CVPR 2014.
Region-based convolutional networks for accurate object detection and segmentation, IEEE PAMI 2016.
语音识别基础
Long short term memory neural computation, Neural computation 9 (8), 1735-1780, 1997. LSTM
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks, ICML 2006.
On the Properties of Neural Machine Translation: Encoder-Decoder Approaches, SSST-8, 2014.
Towards End-To-End Speech Recognition with Recurrent Neural Networks, ICML 2014.
Speech recognition with deep recurrent neural networks, ICASSP 2013.
Hybrid speech recognition with deep bidirectional LSTM, ASRU 2013.
第一次: Speech Recognition
Deep Speech 2 End-to-End Speech Recognition in English and Mandarin, JMLR 2016.
Geoffrey Hinton et al., "Deep neural networks for acoustic modeling in speech recognition." IEEE Signal Processing Magazine 29.6 (2012): 82-97.
EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding, ASRU 2015.
Learning the Speech Front-end With Raw Waveform CLDNNs, InterSpeech 2015.
Convolutional, long short-term memory, fully connected deep neural networks, ICASSP 2015.
Context dependent phone models for LSTM RNN acoustic modelling, ICASSP 2015.
Listen, attend and spell: A neural network for large vocabulary conversational speech recognition, ICASSP 2015.
Audio augmentation for speech recognition, InterSpeech 2015.
第二次: TTS (Text To Speech)
DeepVoice: Real-Time Neural Text-to-Speech
Wavenet: A generative model for raw audio
Char2wav: End-to-end speech synthesis
第二次: Recommender System
[x] Covington P, Adams J, Sargin E. Deep neural networks for youtube recommendations, ACM Recsys, 2016.
[x] Ask the GRU: Multi-task Learning for Deep Text Recommendations
第三次: Machine Translation
[x] Sutskever, I., Vinyals, O. & Le, Q. V. Sequence to sequence learning with neural networks. In Proc. Advances in Neural Information Processing Systems 27, 3104–3112 (2014).
[x] Cho, Kyunghyun, et al., Learning phrase representations using RNN encoder-decoder for statistical machine translation, EMNLP 2014.
第三次: Reinforcement Learning
Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?
Off-Policy Neural Fitted Actor-Critic
A Deep Hierarchical Approach to Lifelong Learning in Minecraft
Guided Deep Reinforcement Learning for Additive Manufacturing Control Application
Deep Visual Foresight for Planning Robot Motion