本人第一篇博客：推荐一本deep learning的入门书籍

一本关于深度学习研究与应用最新进展的小书，共134页，非常紧凑，想了解深度学习的朋友不妨可以看一下。

 DEEP LEARNING: METHODS AND APPLICAITON.

 Li Deng and Dong Yu. Microsoft Research. One Microsoft Way. Redmond, WA 98052. NOW PUBLISHERS, 2014.

Table of Contents
Chapter 1 Introduction .................................................................................................................... 5
1.1 Definitions and Background............................................................................................. 5
1.2 Organization of This Book ............................................................................................... 8
Chapter 2 Some Historical Context of Deep Learning ................................................................ 11
Chapter 3 Three Classes of Deep Learning Networks ................................................................. 18
3.1 A Three-Way Categorization ......................................................................................... 18
3.2 Deep Networks for Unsupervised or Generative Learning ............................................ 21
3.3 Deep Networks for Supervised Learning ....................................................................... 24
3.4 Hybrid Deep Networks................................................................................................... 26
Chapter 4 Deep Autoencoders --- Unsupervised Learning ........................................................... 29
4.1 Introduction .................................................................................................................... 29
4.2 Use of Deep Autoencoders to Extract Speech Features ................................................. 30
4.3 Stacked Denoising Autoencoders................................................................................... 35
4.4 Transforming Autoencoders ........................................................................................... 35
Chapter 5 Pre-Trained Deep Neural Networks --- A Hybrid ...................................................... 37
5.1 Restricted Boltzmann Machines..................................................................................... 37
5.2 Unsupervised Layer-wise Pretraining ............................................................................ 40
5.3 Interfacing DNNs with HMMs ...................................................................................... 42
Chapter 6 Deep Stacking Networks and Variants --- Supervised Learning ................................ 44
6.1 Introduction .................................................................................................................... 44
6.2 A Basic Architecture of the Deep Stacking Network .................................................... 45
6.3 A Method for Learning the DSN Weights ..................................................................... 46
6.4 The Tensor Deep Stacking Network .............................................................................. 48
6.5 The Kernelized Deep Stacking Network ........................................................................ 50
Chapter 7 Selected Applications in Speech and Audio Processing ............................................. 53
7.1 Acoustic Modeling for Speech Recognition................................................................... 53
7.1.1 Back to primitive spectral features of speech................................................................. 54
7.1.2 The DNN-HMM architecture vs. use of DNN-derived features .................................... 56
7.1.3 Noise robustness by deep learning ................................................................................. 59
7.1.4 Output representations in the DNN ................................................................................ 60
7.1.5 Adaptation of the DNN-based speech recognizers ........................................................ 62
7.1.6 Better architectures and nonlinear units ......................................................................... 63
7.1.7 Better optimization and regularization …………………………………………………67
7.2 Speech Synthesis ............................................................................................................ 70

7.3 Audio and Music Processing .......................................................................................... 71

Chapter 8 Selected Applications in Language Modeling and Natural Language Processing ...... 73
8.1 Language Modeling........................................................................................................ 73
8.2 Natural Language Processing ......................................................................................... 77
Chapter 9 Selected Applications in Information Retrieval .......................................................... 84
9.1 A Brief Introduction to Information Retrieval ............................................................... 84
9.2 Semantic Hashing with Deep Autoencoders for Document Indexing and Retrieval ..... 85
9.3 Deep-Structured Semantic Modeling for Document Retrieval ...................................... 86
9.4 Use of Deep Stacking Networks for Information Retrieval ........................................... 91
Chapter 10 Selected Applications in Object Recognition and Computer Vision ........................ 92
10.1 Unsupervised or Generative Feature Learning............................................................... 92
10.2 Supervised Feature Learning and Classification ............................................................ 94
Chapter 11 Selected Applications in Multi-modal and Multi-task Learning ............................. 101
11.1 Multi-Modalities: Text and Image ............................................................................... 101
11.2 Multi-Modalities: Speech and Image ........................................................................... 104
11.3 Multi-Task Learning within the Speech, NLP or Image Domain ................................ 106
Chapter 12 Epilogues ................................................................................................................. 110
BIBLIOGRAPHY ....................................................................................................................... 114

download link: http://research.microsoft.com/pubs/209355/NOW-Book-Revised-Feb2014-online.pdf