Deep Learning with TensorFlow : Explore Neural Networks with Python

"Delve into neural networks, implement deep learning algorithms, and explore layers of data abstraction with the help of this comprehensive TensorFlow guide About This Book * Learn how to implement advanced techniques in deep learning with Google`s brainchild, TensorFlow * Explore deep neural networks and layers of data abstraction with the help of this comprehensive guide * Real-world contextualization through some deep learning problems concerning research and application Who This Book Is For The book is intended for a general audience of people interested in machine learning and machine intelligence. A rudimentary level of programming in one language is assumed, as is a basic familiarity with computer science techniques and technologies, including a basic awareness of computer hardware and algorithms. Some competence in mathematics is needed to the level of elementary linear algebra and calculus. What You Will Learn * Learn about machine learning landscapes along with the historical development and progress of deep learning * Learn about deep machine intelligence and GPU computing with the latest TensorFlow 1.x * Access public datasets and utilize them using TensorFlow to load, process, and transform data * Use TensorFlow on real-world datasets, including images, text, and more * Learn how to evaluate the performance of your deep learning models * Using deep learning for scalable object detection and mobile computing * Train machines quickly to learn from data by exploring reinforcement learning techniques * Explore active areas of deep learning research and applications In Detail Deep learning is the step that comes after machine learning, and has more advanced implementations. Machine learning is not just for academics anymore, but is becoming a mainstream practice through wide adoption, and deep learning has taken the front seat. As a data scientist, if you want to explore data abstraction layers, this book will be your guide. This book shows how this can be exploited in the real world with complex raw data using TensorFlow 1.x. Throughout the book, you`ll learn how to implement deep learning algorithms for machine learning systems and integrate them into your product offerings, including search, image recognition, and language processing. Additionally, you`ll learn how to analyze and improve the performance of deep learning models. This can be done by comparing algorithms against benchmarks, along with machine intelligence, to learn from the information and determine ideal behaviors within a specific context. After finishing the book, you will be familiar with machine learning techniques, in particular the use of TensorFlow for deep learning, and will be ready to apply your knowledge to research or commercial projects. Style and approach This step-by-step guide will explore common, and not so common, deep neural networks and show how these can be exploited in the real world with complex raw data. With the help of practical examples, you will learn how to implement different types of neural nets to build smart applications related to text, speech, and image data processing" -- Dawsonera Cover......Page 1 Copyright......Page 3 Credits......Page 4 About the Authors......Page 5 About the Reviewers......Page 7 www.PacktPub.com......Page 9 Customer Feedback......Page 10 Table of Contents......Page 11 Preface......Page 17 Chapter 1: Getting Started with Deep Learning......Page 23 Supervised learning......Page 24 Reinforcement learning......Page 25 How the human brain works......Page 26 Deep learning history......Page 27 The biological neuron......Page 28 An artificial neuron......Page 29 The backpropagation algorithm......Page 31 Weights optimization......Page 32 Stochastic gradient descent......Page 33 Multilayer perceptron......Page 35 Convolutional Neural Networks......Page 36 Restricted Boltzmann Machines......Page 37 Autoencoders......Page 38 Recurrent Neural Networks......Page 39 Deep learning framework comparisons......Page 40 Summary......Page 44 Chapter 2: First Look at TensorFlow......Page 45 What's new with TensorFlow 1.x?......Page 46 How does it change the way people use it?......Page 47 Installing TensorFlow on Linux......Page 48 Requirements for running TensorFlow with GPU from NVIDIA......Page 49 Step 2: Installing NVIDIA cuDNN v5.1+......Page 50 Step 5: Installing Python (or Python3)......Page 52 Step 6: Installing and upgrading PIP (or PIP3)......Page 53 Installing TensorFlow with native pip......Page 54 Installing with virtualenv......Page 55 Installation from source......Page 57 Computational graphs......Page 59 Why a computational graph?......Page 60 Neural networks as computational graphs......Page 61 The programming model......Page 63 Data model......Page 65 Shape......Page 66 Data types......Page 67 Variables......Page 70 Feeds......Page 71 How does TensorBoard work?......Page 72 Implementing a single input neuron......Page 73 Migrating to TensorFlow 1.x......Page 80 How to upgrade using the script......Page 81 Summary functions......Page 85 Simplified mathematical variants......Page 86 Summary......Page 87 Chapter 3: Using TensorFlow on a Feed-Forward Neural Network......Page 89 Introducing feed-forward neural networks......Page 90 Feed-forward and backpropagation......Page 91 Transfer functions......Page 92 Classification of handwritten digits......Page 94 Exploring the MNIST dataset......Page 95 Softmax classifier......Page 97 Visualization......Page 103 Restoring a model......Page 105 Softmax source code......Page 108 Softmax loader source code......Page 109 Implementing a five-layer neural network......Page 110 Visualization......Page 113 Five-layer neural network source code......Page 115 ReLU classifier......Page 116 Visualization......Page 118 Source code for the ReLU classifier......Page 119 Dropout optimization......Page 121 Visualization......Page 124 Source code for dropout optimization......Page 125 Summary......Page 128 Chapter 4: TensorFlow on a Convolutional Neural Network......Page 129 Introducing CNNs......Page 130 CNN architecture......Page 132 A model for CNNs - LeNet......Page 134 Building your first CNN......Page 135 Source code for a handwritten classifier......Page 144 Emotion recognition with CNNs......Page 146 Source code for emotion classifier......Page 157 Testing the model on your own image......Page 161 Source code......Page 164 Summary......Page 166 Chapter 5: Optimizing TensorFlow Autoencoders......Page 167 Introducing autoencoders......Page 168 Implementing an autoencoder......Page 169 Source code for the autoencoder......Page 175 Improving autoencoder robustness......Page 176 Building a denoising autoencoder......Page 177 Source code for the denoising autoencoder......Page 184 Convolutional autoencoders......Page 186 Decoder......Page 187 Source code for convolutional autoencoder......Page 197 Summary......Page 200 RNNs basic concepts......Page 201 Unfolding an RNN......Page 203 The vanishing gradient problem......Page 204 LSTM networks......Page 205 An image classifier with RNNs......Page 206 Source code for RNN image classifier......Page 212 Bidirectional RNNs......Page 214 Source code for the bidirectional RNN......Page 219 Text prediction......Page 221 PTB model......Page 222 Running the example......Page 223 Summary......Page 225 Chapter 7: GPU Computing......Page 226 GPGPU history......Page 227 The CUDA architecture......Page 228 GPU programming model......Page 229 TensorFlow GPU set up......Page 230 TensorFlow GPU management......Page 233 Programming example......Page 234 Source code for GPU computation......Page 235 Assigning a single GPU on a multi-GPU system......Page 237 Source code for GPU with soft placement......Page 239 Source code for multiple GPUs management......Page 240 Summary......Page 241 Chapter 8: Advanced TensorFlow Programming......Page 242 Introducing Keras......Page 243 Installation......Page 244 Building deep learning models......Page 245 Sentiment classification of movie reviews......Page 247 Source code for the Keras movie classifier......Page 250 Adding a convolutional layer......Page 251 Source code for movie classifier with convolutional layer......Page 252 Pretty Tensor......Page 253 Sequential mode......Page 254 Digit classifier......Page 255 Source code for digit classifier......Page 258 Titanic survival predictor......Page 261 Source code for titanic classifier......Page 265 Summary......Page 266 Introduction to multimedia analysis......Page 267 Deep learning for Scalable Object Detection......Page 268 Using the retrained model......Page 270 Accelerated Linear Algebra......Page 272 Just-in-time compilation via XLA......Page 273 JIT compilation......Page 276 Existence and advantages of XLA......Page 277 Under the hood working of XLA......Page 278 TensorFlow and Keras......Page 279 Effects of having Keras on board......Page 280 Video question answering system......Page 281 Deep learning on Android......Page 288 TensorFlow demo examples......Page 289 Building with Android studio......Page 292 Going deeper - Building with Bazel......Page 293 Summary......Page 295 Chapter 10: Reinforcement Learning......Page 296 Basic concepts of Reinforcement Learning......Page 297 Q-learning algorithm......Page 299 Introducing the OpenAI Gym framework......Page 301 FrozenLake-v0 implementation problem......Page 302 Source code for the FrozenLake-v0 problem......Page 305 Q-learning with TensorFlow......Page 306 Source code for the Q-learning neural network......Page 309 Summary......Page 311 Index......Page 312 Delve into neural networks, implement deep learning algorithms, and explore layers of data abstraction with the help of this comprehensive TensorFlow guideKey Features[•] Learn how to implement advanced techniques in deep learning with Google's brainchild, TensorFlow[•] Explore deep neural networks and layers of data abstraction with the help of this comprehensive guide[•] Real-world contextualization through some deep learning problems concerning research and applicationBook DescriptionDeep learning is the step that comes after machine learning, and has more advanced implementations. Machine learning is not just for academics anymore, but is becoming a mainstream practice through wide adoption, and deep learning has taken the front seat. As a data scientist, if you want to explore data abstraction layers, this book will be your guide. This book shows how this can be exploited in the real world with complex raw data using TensorFlow 1.x. Throughout the book, you'll learn how to implement deep learning algorithms for machine learning systems and integrate them into your product offerings, including search, image recognition, and language processing. Additionally, you'll learn how to analyze and improve the performance of deep learning models. This can be done by comparing algorithms against benchmarks, along with machine intelligence, to learn from the information and determine ideal behaviors within a specific context. After finishing the book, you will be familiar with machine learning techniques, in particular the use of TensorFlow for deep learning, and will be ready to apply your knowledge to research or commercial projects.What you will learn[•]Learn about machine learning landscapes along with the historical development and progress of deep learning[•]Learn about deep machine intelligence and GPU computing with the latest TensorFlow 1.x[•] Access public datasets and utilize them using TensorFlow to load, process, and transform data[•] Use TensorFlow on real-world datasets, including images, text, and more[•] Learn how to evaluate the performance of your deep learning models[•] Using deep learning for scalable object detection and mobile computing[•]Train machines quickly to learn from data by exploring reinforcementlearning techniques[•]Explore active areas of deep learning research and applicationsWho this book is forThe book is intended for a general audience of people interested in machine learning and machine intelligence. A rudimentary level of programming in one language is assumed, as is a basic familiarity with computer science techniques and technologies, including a basic awareness of computer hardware and algorithms. Some competence in mathematics is needed to the level of elementary linear algebra and calculus.