مقدمه‌ای بر کاربردهای تجاری یادگیری عمیق برای توسعه‌دهندگان: از ربات‌های گفت‌وگو در خدمات مشتری تا پردازش تصویر پزشکی

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. Table of Contents......Page 5 About the Authors......Page 12 About the Technical Reviewer......Page 13 Acknowledgments......Page 15 Introduction......Page 16 Part I: Background and Fundamentals......Page 19 Chapter 1: Introduction......Page 20 1.1 Scope and Motivation......Page 21 1.3 Target Audience......Page 23 1.4 Plan and Organization......Page 24 Chapter 2: Deep Learning: An Overview......Page 25 2.1 From a Long Winter to a Blossoming Spring......Page 27 2.2 Why Is DL Different?......Page 30 2.2.1 The Age of the Machines......Page 33 2.2.2 Some Criticism of DL......Page 34 2.3.1 Books......Page 35 2.3.3 Blogs......Page 36 2.3.4 Online Videos and Courses......Page 37 2.3.5 Podcasts......Page 38 2.3.6 Other Web Resources......Page 39 2.3.7 Some Nice Places to Start Playing......Page 40 2.3.8 Conferences......Page 41 2.3.10 DL Frameworks......Page 42 2.3.11 DL As a Service......Page 45 2.4.1 2016......Page 48 2.4.2 2017......Page 49 2.4.3 Evolution Algorithms......Page 50 2.4.4 Creativity......Page 51 Chapter 3: Deep Neural Network Models......Page 52 3.1 A Brief History of Neural Networks......Page 53 3.1.1 The Multilayer Perceptron......Page 55 3.2 What Are Deep Neural Networks?......Page 57 3.3 Boltzmann Machines......Page 60 3.3.1 Restricted Boltzmann Machines......Page 63 Contrastive Divergence......Page 64 3.3.2 Deep Belief Nets......Page 65 3.3.3 Deep Boltzmann Machines......Page 68 3.4 Convolutional Neural Networks......Page 69 3.5 Deep Auto-encoders......Page 70 3.6 Recurrent Neural Networks......Page 71 3.6.1 RNNs for Reinforcement Learning......Page 74 3.6.2 LSTMs......Page 76 3.7 Generative Models......Page 79 3.7.1 Variational Auto-encoders......Page 80 3.7.2 Generative Adversarial Networks......Page 84 Part II: Deep Learning: Core Applications......Page 89 Chapter 4: Image Processing......Page 90 4.1 CNN Models for Image Processing......Page 91 4.2 ImageNet and Beyond......Page 94 4.3 Image Segmentation......Page 99 4.4 Image Captioning......Page 102 4.5 Visual Q&A (VQA)......Page 103 4.6 Video Analysis......Page 107 4.7 GANs and Generative Models......Page 111 4.8 Other Applications......Page 115 4.8.1 Satellite Images......Page 116 4.9 News and Companies......Page 118 4.10 Third-Party Tools and APIs......Page 121 Chapter 5: Natural Language Processing and Speech......Page 123 5.1 Parsing......Page 125 5.2 Distributed Representations......Page 126 5.3 Knowledge Representation and Graphs......Page 128 5.4 Natural Language Translation......Page 135 5.5 Other Applications......Page 139 5.6 Multimodal Learning and Q&A......Page 141 5.7 Speech Recognition......Page 142 5.8 News and Resources......Page 145 5.9 Summary and a Speculative Outlook......Page 148 Chapter 6: Reinforcement Learning and Robotics......Page 149 6.1 What Is Reinforcement Learning?......Page 150 6.2 Traditional RL......Page 152 6.3 DNN for Reinforcement Learning......Page 154 6.3.2 Deep Deterministic Policy Gradient......Page 155 6.3.3 Deep Q-learning......Page 156 6.3.4 Actor-Critic Algorithm......Page 159 6.4 Robotics and Control......Page 162 6.5 Self-Driving Cars......Page 165 6.6 Conversational Bots (Chatbots)......Page 167 6.7 News Chatbots......Page 171 6.8 Applications......Page 173 6.9 Outlook and Future Perspectives......Page 174 6.10 News About Self-Driving Cars......Page 176 Part III: Deep Learning: Business Applications......Page 181 Chapter 7: Recommendation Algorithms and E-commerce......Page 182 7.1 Online User Behavior......Page 183 7.2 Retargeting......Page 184 7.3 Recommendation Algorithms......Page 186 7.3.1 Collaborative Filters......Page 187 7.3.2 Deep Learning Approaches to RSs......Page 189 7.3.3 Item2Vec......Page 191 7.4 Applications of Recommendation Algorithms......Page 192 7.5 Future Directions......Page 193 8.1 The Early Steps in Chess......Page 196 8.2 From Chess to Go......Page 197 8.3.2 Dota......Page 199 8.3.3 Other Applications......Page 200 8.4 Artificial Characters......Page 202 8.5 Applications in Art......Page 203 8.6 Music......Page 206 8.7 Multimodal Learning......Page 208 8.8 Other Applications......Page 209 Chapter 9: Other Applications......Page 217 9.1 Anomaly Detection and Fraud......Page 218 9.1.1 Fraud Prevention......Page 221 9.1.2 Fraud in Online Reviews......Page 223 9.2 Security and Prevention......Page 224 9.3 Forecasting......Page 226 9.3.1 Trading and Hedge Funds......Page 228 9.4 Medicine and Biomedical......Page 231 9.4.1 Image Processing Medical Images......Page 232 9.4.2 Omics......Page 235 9.4.3 Drug Discovery......Page 238 9.5.1 User Experience......Page 240 9.5.2 Big Data......Page 241 9.6 The Future......Page 242 Part IV: Opportunities and Perspectives......Page 244 Chapter 10: Business Impact of DL Technology......Page 245 10.1 Deep Learning Opportunity......Page 247 10.2 Computer Vision......Page 248 10.3 AI Assistants......Page 249 10.4 Legal......Page 251 10.5 Radiology and Medical Imagery......Page 252 10.6 Self-Driving Cars......Page 254 10.8 Building a Competitive Advantage with DL......Page 255 10.9 Talent......Page 257 10.10 It’s Not Only About Accuracy......Page 259 10.11 Risks......Page 260 10.12 When Personal Assistants Become Better Than Us......Page 261 Chapter 11: New Research and Future Directions......Page 263 11.1 Research......Page 264 11.1.1 Attention......Page 265 11.1.2 Multimodal Learning......Page 266 11.1.3 One-Shot Learning......Page 267 11.1.4 Reinforcement Learning and Reasoning......Page 269 11.1.5 Generative Neural Networks......Page 271 11.1.6 Generative Adversarial Neural Networks......Page 272 11.1.7 Knowledge Transfer and Learning How to Learn......Page 274 11.2 When Not to Use Deep Learning......Page 276 11.3 News......Page 277 11.4 Ethics and Implications of AI in Society......Page 279 11.5 Privacy and Public Policy in AI......Page 282 11.6 Startups and VC Investment......Page 284 11.7 The Future......Page 287 11.7.1 Learning with Less Data......Page 289 11.7.3 Multitask Learning......Page 290 11.7.5 Few-Shot Learning......Page 291 11.7.7 Neural Reasoning......Page 292 A.1 The Keras Framework......Page 294 A.1.2 Model......Page 295 A.1.3 The Core Layers......Page 296 A.1.5 Training and Testing......Page 298 A.1.7 Compile and Fit......Page 299 A.2 The Deep and Wide Model......Page 300 A.3 An FCN for Image Segmentation......Page 310 A.3.1 Sequence to Sequence......Page 314 A.4 The Backpropagation on a Multilayer Perceptron......Page 317 References......Page 325 Index......Page 338 A former Wall Street quant sounds an alarm on the mathematical models that pervade modern life — and threaten to rip apart our social fabric We live in the age of the algorithm. Increasingly, the decisions that affect our lives—where we go to school, whether we get a car loan, how much we pay for health insurance—are being made not by humans, but by mathematical models. In theory, this should lead to greater fairness: Everyone is judged according to the same rules, and bias is eliminated. But as Cathy O’Neil reveals in this urgent and necessary book, the opposite is true. The models being used today are opaque, unregulated, and uncontestable, even when they’re wrong. Most troubling, they reinforce discrimination: If a poor student can’t get a loan because a lending model deems him too risky (by virtue of his zip code), he’s then cut off from the kind of education that could pull him out of poverty, and a vicious spiral ensues. Models are propping up the lucky and punishing the downtrodden, creating a “toxic cocktail for democracy.” Welcome to the dark side of Big Data. Tracing the arc of a person’s life, O’Neil exposes the black box models that shape our future, both as individuals and as a society. These “weapons of math destruction” score teachers and students, sort résumés, grant (or deny) loans, evaluate workers, target voters, set parole, and monitor our health. O’Neil calls on modelers to take more responsibility for their algorithms and on policy makers to regulate their use. But in the end, it’s up to us to become more savvy about the models that govern our lives. This important book empowers us to ask the tough questions, uncover the truth, and demand change. — Longlist for National Book Award (Non-Fiction) — Goodreads, semi-finalist for the 2016 Goodreads Choice Awards (Science and Technology) — Kirkus, Best Books of 2016 — New York Times, 100 Notable Books of 2016 (Non-Fiction) — The Guardian, Best Books of 2016 — WBUR’s “On Point,” Best Books of 2016: Staff Picks — Boston Globe, Best Books of 2016, Non-Fiction We live in the age of the algorithm. Increasingly, the decisions that affect our lives (where we go to school, whether we get a car loan, how much we pay for health insurance) are being made not by humans, but by mathematical models. In theory, this should lead to greater fairness: everyone is judged according to the same rules, and bias is eliminated. But as Cathy O'Neil reveals in this book, the opposite is true. The models being used today are opaque, unregulated, and uncontestable, even when they are wrong. Most troubling, they reinforce discrimination: if a poor student can't get a loan because a lending model deems him too risky (by virtue of his zip code), he is then cut off from the kind of education that could pull him out of poverty, and a vicious spiral ensues. Models are propping up the lucky and punishing the downtrodden, creating a 'toxic cocktail for democracy.' Welcome to the dark side of big data. Tracing the arc of a person's life, O'Neil exposes the black box models that shape our future, both as individuals and as a society. These 'weapons of math destruction' score teachers and students, sort résumés, grant (or deny) loans, evaluate workers, target voters, set parole, and monitor our health. O'Neil calls on modelers to take more responsibility for their algorithms and on policy makers to regulate their use. But in the end, it is up to us to become more savvy about the models that govern our lives NEW YORK TIMES BESTSELLER • A former Wall Street quant sounds the alarm on Big Data and the mathematical models that threaten to rip apart our social fabric—with a new afterword “A manual for the twenty-first-century citizen... relevant and urgent.”—Financial Times NATIONAL BOOK AWARD LONGLIST • NAMED ONE OF THE BEST BOOKS OF THE YEAR BY The New York Times Book Review • The Boston Globe • Wired • Fortune • Kirkus Reviews • The Guardian • Nature • On Point We live in the age of the algorithm. Increasingly, the decisions that affect our lives—where we go to school, whether we can get a job or a loan, how much we pay for health insurance—are being made not by humans, but by machines. In theory, this should lead to greater fairness: Everyone is judged according to the same rules. But as mathematician and data scientist Cathy O'Neil reveals, the mathematical models being used today are unregulated and uncontestable, even when they're wrong. Most troubling, they reinforce discrimination—propping up the lucky, punishing the downtrodden, and undermining our democracy in the process. Welcome to the dark side of Big Data. A Former Wall Street Quantitative Analyst Sounds An Alarm On Mathematical Modeling, A Pervasive New Force In Society That Threatens To Undermine Democracy And Widen Inequality,--novelist. Bomb Parts: What Is A Model? -- Shell Shocked: My Journey Of Disillusionment -- Arms Race: Going To College -- Propaganda Machine: Online Advertising -- Civilian Casualties: Justice In The Age Of Big Data -- Ineligible To Serve: Getting A Job -- Sweating Bullets: On The Job -- Collateral Damage: Landing Credit -- No Safe Zone: Getting Insurance -- The Targeted Citizen: Civic Life. Cathy O'neil. Includes Bibliographical References And Index.