Machine Learning with TensorFlow, Second Edition

<b>Updated with new code, new projects, and new chapters, <i>Machine Learning with TensorFlow, Second Edition</i> gives readers a solid foundation in machine-learning concepts and the TensorFlow library.</b><br><br><b>Summary</b><br> Updated with new code, new projects, and new chapters, <i>Machine Learning with TensorFlow, Second Edition</i> gives readers a solid foundation in machine-learning concepts and the TensorFlow library. Written by NASA JPL Deputy CTO and Principal Data Scientist Chris Mattmann, all examples are accompanied by downloadable Jupyter Notebooks for a hands-on experience coding TensorFlow with Python. New and revised content expands coverage of core machine learning algorithms, and advancements in neural networks such as VGG-Face facial identification classifiers and deep speech classifiers.<br> <br> Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.<br> <br> <b>About the technology</b><br> Supercharge your data analysis with machine learning! ML algorithms automatically improve as they process data, so results get better over time. You don’t have to be a mathematician to use ML: Tools like Google’s TensorFlow library help with complex calculations so you can focus on getting the answers you need.<br> <br> <b>About the book</b><br> <i>Machine Learning with TensorFlow, Second Edition</i> is a fully revised guide to building machine learning models using Python and TensorFlow. You’ll apply core ML concepts to real-world challenges, such as sentiment analysis, text classification, and image recognition. Hands-on examples illustrate neural network techniques for deep speech processing, facial identification, and auto-encoding with CIFAR-10.<br> <br> <b>What's inside</b><br> <br> Machine Learning with TensorFlow<br> Choosing the best ML approaches<br> Visualizing algorithms with TensorBoard<br> Sharing results with collaborators<br> Running models in Docker<br> <br> <b>About the reader</b><br> Requires intermediate Python skills and knowledge of general algebraic concepts like vectors and matrices. Examples use the super-stable 1.15.x branch of TensorFlow and TensorFlow 2.x.<br> <br> <b>About the author</b><br> <b>Chris Mattmann</b> is the Division Manager of the Artificial Intelligence, Analytics, and Innovation Organization at NASA Jet Propulsion Lab. The first edition of this book was written by <b>Nishant Shukla</b> with <b>Kenneth Fricklas</b>.<br> <br> Table of Contents<br> <br> PART 1 - YOUR MACHINE-LEARNING RIG<br> <br> 1 A machine-learning odyssey<br> <br> 2 TensorFlow essentials<br> <br> PART 2 - CORE LEARNING ALGORITHMS<br> <br> 3 Linear regression and beyond<br> <br> 4 Using regression for call-center volume prediction<br> <br> 5 A gentle introduction to classification<br> <br> 6 Sentiment classification: Large movie-review dataset<br> <br> 7 Automatically clustering data<br> <br> 8 Inferring user activity from Android accelerometer data<br> <br> 9 Hidden Markov models<br> <br> 10 Part-of-speech tagging and word-sense disambiguation<br> <br> PART 3 - THE NEURAL NETWORK PARADIGM<br> <br> 11 A peek into autoencoders<br> <br> 12 Applying autoencoders: The CIFAR-10 image dataset<br> <br> 13 Reinforcement learning<br> <br> 14 Convolutional neural networks<br> <br> 15 Building a real-world CNN: VGG-Face ad VGG-Face Lite<br> <br> 16 Recurrent neural networks<br> <br> 17 LSTMs and automatic speech recognition<br> <br> 18 Sequence-to-sequence models for chatbots<br> <br> 19 Utility landscape