Hugendubel.info - Die B2B Online-Buchhandlung 

Merkliste
Die Merkliste ist leer.
Bitte warten - die Druckansicht der Seite wird vorbereitet.
Der Druckdialog öffnet sich, sobald die Seite vollständig geladen wurde.
Sollte die Druckvorschau unvollständig sein, bitte schliessen und "Erneut drucken" wählen.

Deep Learning Illustrated

A Visual, Interactive Guide to Artificial Intelligence
TaschenbuchKartoniert, Paperback
416 Seiten
Englisch
Pearson Education (US)erschienen am17.12.2019
"The authors´ clear visual style provides a comprehensive look at what´s currently possible with artificial neural networks as well as a glimpse of the magic that´s to come."-Tim Urban, author of Wait But Why Fully Practical, Insightful Guide to Modern Deep LearningDeep learning is transforming software, facilitating powerful new artificial intelligence capabilities, and driving unprecedented algorithm performance. Deep Learning Illustrated is uniquely intuitive and offers a complete introduction to the discipline´s techniques. Packed with full-color figures and easy-to-follow code, it sweeps away the complexity of building deep learning models, making the subject approachable and fun to learn.World-class instructor and practitioner Jon Krohn-with visionary content from Grant Beyleveld and beautiful illustrations by Aglaé Bassens-presents straightforward analogies to explain what deep learning is, why it has become so popular, and how it relates to other machine learning approaches. Krohn has created a practical reference and tutorial for developers, data scientists, researchers, analysts, and students who want to start applying it. He illuminates theory with hands-on Python code in accompanying Jupyter notebooks. To help you progress quickly, he focuses on the versatile deep learning library Keras to nimbly construct efficient TensorFlow models; PyTorch, the leading alternative library, is also covered.You´ll gain a pragmatic understanding of all major deep learning approaches and their uses in applications ranging from machine vision and natural language processing to image generation and game-playing algorithms. Discover what makes deep learning systems unique, and the implications for practitionersExplore new tools that make deep learning models easier to build, use, and improveMaster essential theory: artificial neurons, training, optimization, convolutional nets, recurrent nets, generative adversarial networks (GANs), deep reinforcement learning, and moreWalk through building interactive deep learning applications, and move forward with your own artificial intelligence projects Register your book for convenient access to downloads, updates, and/or corrections as they become available. See inside book for details.mehr
Verfügbare Formate
TaschenbuchKartoniert, Paperback
EUR53,50
E-BookPDF1 - PDF WatermarkE-Book
EUR44,49
E-BookEPUBePub WasserzeichenE-Book
EUR44,49

Produkt

Klappentext"The authors´ clear visual style provides a comprehensive look at what´s currently possible with artificial neural networks as well as a glimpse of the magic that´s to come."-Tim Urban, author of Wait But Why Fully Practical, Insightful Guide to Modern Deep LearningDeep learning is transforming software, facilitating powerful new artificial intelligence capabilities, and driving unprecedented algorithm performance. Deep Learning Illustrated is uniquely intuitive and offers a complete introduction to the discipline´s techniques. Packed with full-color figures and easy-to-follow code, it sweeps away the complexity of building deep learning models, making the subject approachable and fun to learn.World-class instructor and practitioner Jon Krohn-with visionary content from Grant Beyleveld and beautiful illustrations by Aglaé Bassens-presents straightforward analogies to explain what deep learning is, why it has become so popular, and how it relates to other machine learning approaches. Krohn has created a practical reference and tutorial for developers, data scientists, researchers, analysts, and students who want to start applying it. He illuminates theory with hands-on Python code in accompanying Jupyter notebooks. To help you progress quickly, he focuses on the versatile deep learning library Keras to nimbly construct efficient TensorFlow models; PyTorch, the leading alternative library, is also covered.You´ll gain a pragmatic understanding of all major deep learning approaches and their uses in applications ranging from machine vision and natural language processing to image generation and game-playing algorithms. Discover what makes deep learning systems unique, and the implications for practitionersExplore new tools that make deep learning models easier to build, use, and improveMaster essential theory: artificial neurons, training, optimization, convolutional nets, recurrent nets, generative adversarial networks (GANs), deep reinforcement learning, and moreWalk through building interactive deep learning applications, and move forward with your own artificial intelligence projects Register your book for convenient access to downloads, updates, and/or corrections as they become available. See inside book for details.
Details
ISBN/GTIN978-0-13-511669-2
ProduktartTaschenbuch
EinbandartKartoniert, Paperback
Erscheinungsjahr2019
Erscheinungsdatum17.12.2019
Seiten416 Seiten
SpracheEnglisch
MasseBreite 179 mm, Höhe 231 mm, Dicke 22 mm
Gewicht766 g
Artikel-Nr.47739115

Inhalt/Kritik

Inhaltsverzeichnis
Figures xixTables xxviiExamples xxixForeword xxxiiiPreface xxxvAcknowledgments xxxixAbout the Authors xliPart I: Introducing Deep Learning 1Chapter 1: Biological and Machine Vision 3Biological Vision 3Machine Vision 8TensorFlow Playground 17Quick, Draw! 19Summary 19Chapter 2: Human and Machine Language 21Deep Learning for Natural LanguageProcessing 21Computational Representations of Language 25Elements of Natural Human Language 33Google Duplex 35Summary 37Chapter 3: Machine Art 39A Boozy All-Nighter 39Arithmetic on Fake Human Faces 41Style Transfer: Converting Photos into Monet (and Vice Versa) 44Make Your Own Sketches Photorealistic 45Creating Photorealistic Images from Text 45Image Processing Using Deep Learning 46Summary 48Chapter 4: Game-Playing Machines 49Deep Learning, AI, and Other Beasts 49Three Categories of Machine Learning Problems 53Deep Reinforcement Learning 56Video Games 57Board Games 59Manipulation of Objects 67Popular Deep Reinforcement Learning Environments 68Three Categories of AI 71Summary 72Part II: Essential Theory Illustrated 73Chapter 5: The (Code) Cart Ahead of the (Theory)Horse 75Prerequisites 75Installation 76A Shallow Network in Keras 76Summary 84Chapter 6: Artificial Neurons Detecting Hot Dogs 85Biological Neuroanatomy 101 85The Perceptron 86Modern Neurons and Activation Functions 91Choosing a Neuron 96Summary 96Key Concepts 97Chapter 7: Artificial Neural Networks 99The Input Layer 99Dense Layers 99A Hot Dog-Detecting Dense Network 101The Softmax Layer of a Fast Food-Classifying Network 106Revisiting Our Shallow Network 108Summary 110Key Concepts 110Chapter 8: Training Deep Networks 111Cost Functions 111Optimization: Learning to Minimize Cost 115Backpropagation 124Tuning Hidden-Layer Count and NeuronCount 125An Intermediate Net in Keras 127Summary 129Key Concepts 130Chapter 9: Improving Deep Networks 131Weight Initialization 131Unstable Gradients 137Model Generalization (Avoiding Overfitting) 140Fancy Optimizers 145A Deep Neural Network inKeras 147Regression 149TensorBoard 152Summary 154Key Concepts 155Part III: Interactive Applications of Deep Learning 157Chapter 10: Machine Vision 159Convolutional Neural Networks 159Pooling Layers 169LeNet-5 in Keras 171AlexNet and VGGNet in Keras 176Residual Networks 179Applications of Machine Vision 182Summary 193Key Concepts 193Chapter 11: Natural Language Processing 195Preprocessing Natural Language Data 195Creating Word Embeddings with word2vec 206The Area under the ROC Curve 217Natural Language Classification with Familiar Networks 222Networks Designed for Sequential Data 240Non-sequential Architectures: The Keras Functional API 251Summary 256Key Concepts 257Chapter 12: Generative Adversarial Networks 259Essential GAN Theory 259The Quick, Draw! Dataset 263The Discriminator Network 266The Generator Network 269The Adversarial Network 272GAN Training 275Summary 281Key Concepts 282Chapter 13: Deep Reinforcement Learning 283Essential Theory of Reinforcement Learning 283Essential Theory of Deep Q-Learning Networks 290Defining a DQN Agent 293Interacting with an OpenAI Gym Environment 300Hyperparameter Optimization with SLM Lab 303Agents Beyond DQN 306Summary 308Key Concepts 309Part IV: You and AI 311Chapter 14: Moving Forward with Your Own Deep Learning Projects 313Ideas for Deep Learning Projects 313Resources for Further Projects 317The Modeling Process, Including Hyperparameter Tuning 318Deep Learning Libraries 321Software 2.0 324Approaching Artificial General Intelligence 326Summary 328Part V: Appendices 331Appendix A: Formal Neural Network Notation 333Appendix B: Backpropagation 335Appendix C: PyTorch 339PyTorch Features 339PyTorch in Practice 341Index 345mehr

Autor

Jon Krohn is the chief data scientist at untapt, a machine learning startup in New York. He leads a flourishing Deep Learning Study Group, presents the acclaimed Deep Learning with TensorFlow LiveLessons in Safari, and teaches his Deep Learning curriculum at the NYC Data Science Academy. Jon holds a doctorate in neuroscience from Oxford University and has been publishing on machine learning in leading academic journals since 2010. Grant Beyleveld is a doctoral candidate at the Icahn School of Medicine at New York's Mount Sinai hospital, researching the relationship between viruses and their hosts. A founding member of the Deep Learning Study Group, he holds a masters in molecular medicine and medical biochemistry from the University of Witwatersrand. Aglaé Bassens is a Belgian artist based in Brooklyn. She studied fine arts at The Ruskin School of Drawing and Fine Art, Oxford University, and University College London's Slade School of Fine Arts. Along with her work as an illustrator, her practice includes still life painting and murals.