Introduction to Deep Learning Business Applications for Developers (eBook)

From Conversational Bots in Customer Service to Medical Image Processing

Armando Vieira, Bernardete Ribeiro (Autoren)

eBook Download: PDF

2018 | First Edition
XXI, 343 Seiten
Apress (Verlag)
978-1-4842-3453-2 (ISBN)

Infos

Discover the potential applications, challenges, and opportunities of deep learning from a business perspective with technical examples. These applications include image recognition, segmentation and annotation, video processing and annotation, voice recognition, intelligent personal assistants, automated translation, and autonomous vehicles. 

An Introduction to Deep Learning Business Applications for Developers covers some common DL algorithms such as content-based recommendation algorithms and natural language processing. You'll explore examples, such as video prediction with fully convolutional neural networks (FCNN) and residual neural networks (ResNets). You will also see applications of DL for controlling robotics, exploring the DeepQ learning algorithm with Monte Carlo Tree search (used to beat humans in the game of Go), and modeling for financial risk assessment. There will also be mention of the powerful set of algorithms called Generative Adversarial Neural networks (GANs) that can be applied for image colorization, image completion, and style transfer.

After reading this book you will have an overview of the exciting field of deep neural networks and an understanding of most of the major applications of deep learning. The book contains some coding examples, tricks, and insights on how to train deep learning models using the Keras framework.

What You Will Learn

• Find out about deep learning and why it is so powerful
  
• Work with the major algorithms available to train deep learning models
  
• See the major breakthroughs in terms of applications of deep learning  
  
• Run simple examples with a selection of deep learning libraries 
  
• Discover the areas of impact of deep learning in business
  

Who This Book Is For 

Data scientists, entrepreneurs, and business developers.

Dr Armando Vieira is a Data Scientist and Artificial Intelligence consultant with an entrepreneurial mindset. Passionate about how to make Machine Learning projects work for organizations and how to build great AI based products.As algorithms are becoming a commodity, the challenge is not building them but using them to solve real problems.

Have coordinated several projects on Credit Risk Evaluation, Recommendation Systems, Clustering Analysis and Predictive Analytics. 

Bernardete Ribeiro is Professor at University of Coimbra, Portugal. She has a Ph.D. and Habilitation in Informatics Engineering. She is Director of the Center of Informatics and Systems of the University of Coimbra (CISUC).She is President of the Portuguese Association of Pattern Recognition (APRP). She is Founder and Director of the Laboratory of Artificial Neural Networks (LARN) for more than 20 years. She is IEEE SMC Senior member, member of International Association of Pattern Recognition (IAPR), International Neural Network Society (INNS), and ACM. Her research interests are in the areas of Machine Learning, Pattern Recognition, and their applications to abroad range of fields. She is author or co-author of over three hundred publications including books, journalsand international and national conferences. She has delivered numerous invited talks, seminars, and short courses.

Inhalt

Table of Contents 5
About the Authors 12
About the Technical Reviewer 13
Acknowledgments 15
Introduction 16
Part I: Background and Fundamentals 19
Chapter 1: Introduction 20
1.1 Scope and Motivation 21
1.2 Challenges in the Deep Learning Field 23
1.3 Target Audience 23
1.4 Plan and Organization 24
Chapter 2: Deep Learning: An Overview 25
2.1 From a Long Winter to a Blossoming Spring 27
2.2 Why Is DL Different? 30
2.2.1 The Age of the Machines 33
2.2.2 Some Criticism of DL 34
2.3 Resources 35
2.3.1 Books 35
2.3.2 Newsletters 36
2.3.3 Blogs 36
2.3.4 Online Videos and Courses 37
2.3.5 Podcasts 38
2.3.6 Other Web Resources 39
2.3.7 Some Nice Places to Start Playing 40
2.3.8 Conferences 41
2.3.9 Other Resources 42
2.3.10 DL Frameworks 42
2.3.11 DL As a Service 45
2.4 Recent Developments 48
2.4.1 2016 48
2.4.2 2017 49
2.4.3 Evolution Algorithms 50
2.4.4 Creativity 51
Chapter 3: Deep Neural Network Models 52
3.1 A Brief History of Neural Networks 53
3.1.1 The Multilayer Perceptron 55
3.2 What Are Deep Neural Networks? 57
3.3 Boltzmann Machines 60
3.3.1 Restricted Boltzmann Machines 63
Contrastive Divergence 64
3.3.2 Deep Belief Nets 65
3.3.3 Deep Boltzmann Machines 68
3.4 Convolutional Neural Networks 69
3.5 Deep Auto-encoders 70
3.6 Recurrent Neural Networks 71
3.6.1 RNNs for Reinforcement Learning 74
3.6.2 LSTMs 76
3.7 Generative Models 79
3.7.1 Variational Auto-encoders 80
3.7.2 Generative Adversarial Networks 84
Part II: Deep Learning: Core Applications 89
Chapter 4: Image Processing 90
4.1 CNN Models for Image Processing 91
4.2 ImageNet and Beyond 94
4.3 Image Segmentation 99
4.4 Image Captioning 102
4.5 Visual Q& A (VQA)
4.6 Video Analysis 107
4.7 GANs and Generative Models 111
4.8 Other Applications 115
4.8.1 Satellite Images 116
4.9 News and Companies 118
4.10 Third-Party Tools and APIs 121
Chapter 5: Natural Language Processing and Speech 123
5.1 Parsing 125
5.2 Distributed Representations 126
5.3 Knowledge Representation and Graphs 128
5.4 Natural Language Translation 135
5.5 Other Applications 139
5.6 Multimodal Learning and Q& A
5.7 Speech Recognition 142
5.8 News and Resources 145
5.9 Summary and a Speculative Outlook 148
Chapter 6: Reinforcement Learning and Robotics 149
6.1 What Is Reinforcement Learning? 150
6.2 Traditional RL 152
6.3 DNN for Reinforcement Learning 154
6.3.1 Deterministic Policy Gradient 155
6.3.2 Deep Deterministic Policy Gradient 155
6.3.3 Deep Q-learning 156
6.3.4 Actor-Critic Algorithm 159
6.4 Robotics and Control 162
6.5 Self-Driving Cars 165
6.6 Conversational Bots (Chatbots) 167
6.7 News Chatbots 171
6.8 Applications 173
6.9 Outlook and Future Perspectives 174
6.10 News About Self-Driving Cars 176
Part III: Deep Learning: Business Applications 181
Chapter 7: Recommendation Algorithms and E-commerce 182
7.1 Online User Behavior 183
7.2 Retargeting 184
7.3 Recommendation Algorithms 186
7.3.1 Collaborative Filters 187
7.3.2 Deep Learning Approaches to RSs 189
7.3.3 Item2Vec 191
7.4 Applications of Recommendation Algorithms 192
7.5 Future Directions 193
Chapter 8: Games and Art 196
8.1 The Early Steps in Chess 196
8.2 From Chess to Go 197
8.3 Other Games and News 199
8.3.1 Doom 199
8.3.2 Dota 199
8.3.3 Other Applications 200
8.4 Artificial Characters 202
8.5 Applications in Art 203
8.6 Music 206
8.7 Multimodal Learning 208
8.8 Other Applications 209
Chapter 9: Other Applications 217
9.1 Anomaly Detection and Fraud 218
9.1.1 Fraud Prevention 221
9.1.2 Fraud in Online Reviews 223
9.2 Security and Prevention 224
9.3 Forecasting 226
9.3.1 Trading and Hedge Funds 228
9.4 Medicine and Biomedical 231
9.4.1 Image Processing Medical Images 232
9.4.2 Omics 235
9.4.3 Drug Discovery 238
9.5 Other Applications 240
9.5.1 User Experience 240
9.5.2 Big Data 241
9.6 The Future 242
Part IV: Opportunities and Perspectives 244
Chapter 10: Business Impact of DL Technology 245
10.1 Deep Learning Opportunity 247
10.2 Computer Vision 248
10.3 AI Assistants 249
10.4 Legal 251
10.5 Radiology and Medical Imagery 252
10.6 Self-Driving Cars 254
10.7 Data Centers 255
10.8 Building a Competitive Advantage with DL 255
10.9 Talent 257
10.10 It’s Not Only About Accuracy 259
10.11 Risks 260
10.12 When Personal Assistants Become Better Than Us 261
Chapter 11: New Research and Future Directions 263
11.1 Research 264
11.1.1 Attention 265
11.1.2 Multimodal Learning 266
11.1.3 One-Shot Learning 267
11.1.4 Reinforcement Learning and Reasoning 269
11.1.5 Generative Neural Networks 271
11.1.6 Generative Adversarial Neural Networks 272
11.1.7 Knowledge Transfer and Learning How to Learn 274
11.2 When Not to Use Deep Learning 276
11.3 News 277
11.4 Ethics and Implications of AI in Society 279
11.5 Privacy and Public Policy in AI 282
11.6 Startups and VC Investment 284
11.7 The Future 287
11.7.1 Learning with Less Data 289
11.7.2 Transfer Learning 290
11.7.3 Multitask Learning 290
11.7.4 Adversarial Learning 291
11.7.5 Few-Shot Learning 291
11.7.6 Metalearning 292
11.7.7 Neural Reasoning 292
Appendix A:Training DNN with Keras 294
A.1 The Keras Framework 294
A.1.1 Installing Keras in Linux 295
A.1.2 Model 295
A.1.3 The Core Layers 296
A.1.4 The Loss Function 298
A.1.5 Training and Testing 298
A.1.6 Callbacks 299
A.1.7 Compile and Fit 299
A.2 The Deep and Wide Model 300
A.3 An FCN for Image Segmentation 310
A.3.1 Sequence to Sequence 314
A.4 The Backpropagation on a Multilayer Perceptron 317
References 325
Index 338

Produkt-Details

• Erscheint lt. Verlag: 2.5.2018
• Zusatzinfo: XXI, 343 p. 64 illus.
• Verlagsort: Berkeley
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Programmiersprachen / -werkzeuge
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Schlagworte: convolutional neural networks • Deep learning • deep neural networks • Natural Language Processing • Python • Recommendation Alorithms • Reinforcement Learning • Robotics
• ISBN-10: 1-4842-3453-7 / 1484234537
• ISBN-13: 978-1-4842-3453-2 / 9781484234532