Learning Deep Learning

NVIDIA's Full-Color Guide to Deep Learning: All You Need to Get Started and Get Results "To enable everyone to be part of this historic revolution requires the democratization of AI knowledge and resources. This book is timely and relevant towards accomplishing these lofty goals." -- From the foreword by Dr. Anima Anandkumar, Bren Professor, Caltech, and Director of ML Research, NVIDIA "Ekman uses a learning technique that in our experience has proven pivotal to success-asking the reader to think about using DL techniques in practice. His straightforward approach is refreshing, and he permits the reader to dream, just a bit, about where DL may yet take us." -- From the foreword by Dr. Craig Clawson, Director, NVIDIA Deep Learning Institute
Deep learning (DL) is a key component of today's exciting advances in machine learning and artificial intelligence. Learning Deep Learning is a complete guide to DL. Illuminating both the core concepts and the hands-on programming techniques needed to succeed, this book is ideal for developers, data scientists, analysts, and others--including those with no prior machine learning or statistics experience. After introducing the essential building blocks of deep neural networks, such as artificial neurons and fully connected, convolutional, and recurrent layers, Magnus Ekman shows how to use them to build advanced architectures, including the Transformer. He describes how these concepts are used to build modern networks for computer vision and natural language processing (NLP), including Mask R-CNN, GPT, and BERT. And he explains how a natural language translator and a system generating natural language descriptions of images. Throughout, Ekman provides concise, well-annotated code examples using TensorFlow with Keras. Corresponding PyTorch examples are provided online, and the book thereby covers the two dominating Python libraries for DL used in industry and academia. He concludes with an introduction to neural architecture search (NAS), exploring important ethical issues and providing resources for further learning.

• Explore and master core concepts: perceptrons, gradient-based learning, sigmoid neurons, and back propagation
• See how DL frameworks make it easier to develop more complicated and useful neural networks
• Discover how convolutional neural networks (CNNs) revolutionize image classification and analysis
• Apply recurrent neural networks (RNNs) and long short-term memory (LSTM) to text and other variable-length sequences
• Master NLP with sequence-to-sequence networks and the Transformer architecture

• Build applications for natural language translation and image captioning
  NVIDIA's invention of the GPU sparked the PC gaming market. The company's pioneering work in accelerated computing--a supercharged form of computing at the intersection of computer graphics, high-performance computing, and AI--is reshaping trillion-dollar industries, such as transportation, healthcare, and manufacturing, and fueling the growth of many others. Register your book for convenient access to downloads, updates, and/or corrections as they become available. See inside book for details.

Autorentext

Magnus Ekman, Ph.D., is a director of architecture at NVIDIA Corporation. His doctorate is in computer engineering, and he is the inventor of multiple patents. He was first exposed to artificial neural networks in the late nineties in his native country, Sweden. After some dabbling in evolutionary computation, he ended up focusing on computer architecture and relocated to Silicon Valley, where he lives with his wife Jennifer, children Sebastian and Sofia, and dog Babette. He previously worked with processor design and R&D at Sun Microsystems and Samsung Research America, and has been involved in starting two companies, one of which (Skout) was later acquired by The Meet Group, Inc. In his current role at NVIDIA, he leads an engineering team working on CPU performance and power efficiency for system on chips targeting the autonomous vehicle market. As the Deep Learning (DL) field exploded the past few years, fueled by NVIDIA's GPU technology and CUDA, Dr. Ekman found himself in the middle of a company expanding beyond computer graphics into becoming a deep learning (DL) powerhouse. As a part of that journey, he challenged himself to stay up-to-date with the most recent developments in the field. He considers himself to be an educator, and in the process of writing Learning Deep Learning ( LDL), he partnered with the NVIDIA Deep Learning Institute (DLI), which offers hands-on training in AI, accelerated computing, and accelerated data science. He is thrilled about DLI's plans to add LDL to its existing portfolio of self-paced online courses, live instructor-led workshops, educator programs, and teaching kits.

Inhalt

Foreword by Dr. Anima Anandkumar xxi
Foreword by Dr. Craig Clawson xxiii
Preface xxv
Acknowledgments li
About the Author liii

Chapter 1: The Rosenblatt Perceptron 1
Example of a Two-Input Perceptron 4
The Perceptron Learning Algorithm 7
Limitations of the Perceptron 15
Combining Multiple Perceptrons 17
Implementing Perceptrons with Linear Algebra 20
Geometric Interpretation of the Perceptron 30
Understanding the Bias Term 33
Concluding Remarks on the Perceptron 34

Chapter 2: Gradient-Based Learning 37
Intuitive Explanation of the Perceptron Learning Algorithm 37
Derivatives and Optimization Problems 41
Solving a Learning Problem with Gradient Descent 44
Constants and Variables in a Network 48
Analytic Explanation of the Perceptron Learning Algorithm 49
Geometric Description of the Perceptron Learning Algorithm 51
Revisiting Different Types of Perceptron Plots 52
Using a Perceptron to Identify Patterns 54
Concluding Remarks on Gradient-Based Learning 57

Chapter 3: Sigmoid Neurons and Backpropagation 59
Modified Neurons to Enable Gradient Descent for Multilevel Networks 60
Which Activation Function Should We Use? 66
Function Composition and the Chain Rule 67
Using Backpropagation to Compute the Gradient 69
Backpropagation with Multiple Neurons per Layer 81
Programming Example: Learning the XOR Function 82
Network Architectures 87
Concluding Remarks on Backpropagation 89

Chapter 4: Fully Connected Networks Applied to Multiclass Classification 91
Introduction to Datasets Used When Training Networks 92
Training and Inference 100
Extending the Network and Learning Algorithm to Do Multiclass Classification 101
Network for Digit Classification 102
Loss Function for Multiclass Classification 103
Programming Example: Classifying Handwritten Digits 104
Mini-Batch Gradient Descent 114
Concluding Remarks on Multiclass Classification 115

Chapter 5: Toward DL: Frameworks and Network Tweaks 117
Programming Example: Moving to a DL Framework 118
The Problem of Saturated Neurons and Vanishing Gradients 124
Initialization and Normalization Techniques to Avoid Saturated Neurons 126
Cross-Entropy Loss Function to Mitigate Effect of Saturated Output Neurons 130
Different Activation Functions to Avoid Vanishing Gradient in Hidden Layers 136
Variations on Gradient Descent to Improve Learning 141
Experiment: Tweaking Network and Learning Parameters 143
Hyperparameter Tuning and Cross-Validation 146
Concluding Remarks on the Path Toward Deep Learning 150

Chapter 6: Fully Connected Networks Applied to Regression 153
Output Units 154
The Boston Housing Dataset 160
Programming Example: Predicting House Prices with a DNN 161
Improving Generalization with Regularization 166
Experiment: Deeper and Regularized Models for House Price Prediction 169
Concluding Remarks on Output Units and Regression Problems 170

Chapter 7: Convolu…