As part of the best-selling Pocket Primer series, this book is designed to introduce beginners to basic machine learning algorithms using TensorFlow 2. It is intended to be a fast-paced introduction to various “core” features of TensorFlow, with code samples that cover machine learning and TensorFlow basics. A comprehensive appendix contains some Keras-based code samples and the underpinnings of MLPs, CNNs, RNNs, and LSTMs. The material in the chapters illustrates how to solve a variety of tasks after which you can do further reading to deepen your knowledge. Companion files with all of the code samples are available for downloading from the publisher by emailing proof of purchase to [email protected]. Features: Uses Python for code samples Covers TensorFlow 2 APIs and Datasets Includes a comprehensive appendix that covers Keras and advanced topics such as NLPs, MLPs, RNNs, LSTMs Features the companion files with all of the source code examples and figures (download from the publisher)

As part of the best-selling Pocket Primer series, this book is designed to introduce the reader to basic deep learning concepts and incorporate that knowledge into Angular 10 applications. It is intended to be a fast-paced introduction to some basic features of deep learning and an overview of several popular deep learning classifiers. The book includes code samples and numerous figures and covers topics such as Angular 10 functionality, basic deep learning concepts, classification algorithms, TensorFlow, and Keras. Companion files with code and color figures are included. FEATURES: Introduces basic deep learning concepts and Angular 10 applications Covers MLPs (MultiLayer Perceptrons) and CNNs (Convolutional Neural Networks), RNNs (Recurrent Neural Networks), LSTMs (Long Short-Term Memory), GRUs (Gated Recurrent Units), autoencoders, and GANs (Generative Adversarial Networks) Introduces TensorFlow 2 and Keras Includes companion files with source code and 4-color figures. The companion files are also available online by emailing the publisher with proof of purchase at [email protected].

As part of the best-selling Pocket Primer series, this book is designed to introduce the reader to basic machine learning concepts and incorporate that knowledge into Angular applications. The book is intended to be a fast-paced introduction to some basic features of machine learning and an overview of several popular machine learning classifiers. It includes code samples and numerous figures and covers topics such as Angular functionality, basic machine learning concepts, classification algorithms, TensorFlow and Keras. The files with code and color figures are on the companion disc with the book or available from the publisher. Features: Introduces the basic machine learning concepts and Angular applications Includes source code and full color figures

As part of the best-selling Pocket Primer series, this book is designed to introduce beginners to TensorFlow 1.x fundamentals for basic machine learning algorithms in TensorFlow. It is intended to be a fast-paced introduction to various “core” features of TensorFlow, with code samples that cover deep learning and TensorFlow basics. The material in the chapters illustrates how to solve a variety of tasks after which you can do further reading to deepen your knowledge. Companion files with all of the code samples are available for downloading from the publisher by writing to [email protected]. Features: Uses Python for code samples Covers TensorFlow APIs and Datasets Assumes the reader has very limited experience Companion files with all of the source code examples (download from the publisher)

This book begins with an introduction to AI, followed by machine learning, deep learning, NLP, and reinforcement learning. Readers will learn about machine learning classifiers such as logistic regression, k-NN, decision trees, random forests, and SVMs. Next, the book covers deep learning architectures such as CNNs, RNNs, LSTMs, and auto encoders. Keras-based code samples are included to supplement the theoretical discussion. In addition, this book contains appendices for Keras, TensorFlow 2, and Pandas. Features: Covers an introduction to programming concepts related to AI, machine learning, and deep learning Includes material on Keras, TensorFlow2 and Pandas

As part of the new Pocket Primer series, this book provides an overview of the major aspects and the source code to use Python 2. It covers the latest Python developments, built-in functions and custom classes, data visualization, graphics, databases, and more. It includes a companion disc with appendices, source code, and figures. This Pocket Primer is primarily for self-directed learners who want to learn Python 2 and it serves as a starting point for deeper exploration of Python programming. Features: +Includes a companion disc with appendices, source code, and figures +Contains material devoted to Raspberry Pi, Roomba, JSON, and Jython +Includes latest Python 2 developments, built-in functions and custom classes, data visualization, graphics, databases, and more +Provides a solid introduction to Python 2 via complete code samples On the CD-ROM: +Appendices (HTML5 and JavaScript Toolkits, Jython, SPA) +Source code samples +All images from the text (including 4-color) +Solutions to Odd-Numbered Exercises

As part of the best-selling Pocket Primer series, this book is designed to prepare programmers for machine learning and deep learning/TensorFlow topics. It begins with a quick introduction to Python, followed by chapters that discuss NumPy, Pandas, Matplotlib, and scikit-learn. The final two chapters contain an assortment of TensorFlow 1.x code samples, including detailed code samples for TensorFlow Dataset (which is used heavily in TensorFlow 2 as well). A TensorFlow Dataset refers to the classes in the tf.data.Dataset namespace that enables programmers to construct a pipeline of data by means of method chaining so-called lazy operators, e.g., map(), filter(), batch(), and so forth, based on data from one or more data sources. Companion files with source code are available for downloading from the publisher by writing [email protected]. Features: A practical introduction to Python, NumPy, Pandas, Matplotlib, and introductory aspects of TensorFlow 1.x Contains relevant NumPy/Pandas code samples that are typical in machine learning topics, and also useful TensorFlow 1.x code samples for deep learning/TensorFlow topics Includes many examples of TensorFlow Dataset APIs with lazy operators, e.g., map(), filter(), batch(), take() and also method chaining such operators Assumes the reader has very limited experience Companion files with all of the source code examples (download from the publisher)

As part of the best-selling Pocket Primer series, this book is designed to introduce the reader to the basic concepts of data science using Python 3 and other computer applications. It is intended to be a fast-paced introduction to some basic features of data analytics and also covers statistics, data visualization, linear algebra, and regular expressions. The book includes numerous code samples using Python, NumPy, R, SQL, NoSQL, and Pandas. Companion files with source code and color figures are available. FEATURES: Includes a concise introduction to Python 3 and linear algebra Provides a thorough introduction to data visualization and regular expressions Covers NumPy, Pandas, R, and SQL Introduces probability and statistical concepts Features numerous code samples throughout Companion files with source code and figures

As part of the best-selling Pocket Primer series, this book is designed to introduce readers to an assortment of useful command-line utilities that can be combined to create simple, yet powerful shell scripts. While all examples and scripts use the “bash” command set, many of the concepts translate into other command shells (such as sh, ksh, zsh, and csh), including the concept of piping data between commands and the highly versatile sed and awk commands. Aimed at a reader relatively new to working in a bash environment, the book is comprehensive enough to be a good reference and teach a few new techniques to those who already have some experience with creating shell scripts. It contains a variety of code fragments and shell scripts for data scientists, data analysts, and other people who want shell-based solutions to “clean” various types of text files. In addition, the concepts and code samples in this book are useful for people who want to simplify routine tasks. Includes companion files with all of the source code examples (download from the publisher by writing to [email protected]). Features: Takes introductory concepts and commands in bash, and then demonstrates their uses in simple, yet powerful shell scripts Contains an assortment of shell scripts for data scientists, data analysts, and other people who want shell-based solutions to “clean” various types of text files Includes companion files with all of the source code examples (available for download from the publisher)

An accessible introduction to the artificial intelligence technology that enables computer vision, speech recognition, machine translation, and driverless cars. Deep learning is an artificial intelligence technology that enables computer vision, speech recognition in mobile phones, machine translation, AI games, driverless cars, and other applications. When we use consumer products from Google, Microsoft, Facebook, Apple, or Baidu, we are often interacting with a deep learning system. In this volume in the MIT Press Essential Knowledge series, computer scientist John Kelleher offers an accessible and concise but comprehensive introduction to the fundamental technology at the heart of the artificial intelligence revolution. Kelleher explains that deep learning enables data-driven decisions by identifying and extracting patterns from large datasets; its ability to learn from complex data makes deep learning ideally suited to take advantage of the rapid growth in big data and computational power. Kelleher also explains some of the basic concepts in deep learning, presents a history of advances in the field, and discusses the current state of the art. He describes the most important deep learning architectures, including autoencoders, recurrent neural networks, and long short-term networks, as well as such recent developments as Generative Adversarial Networks and capsule networks. He also provides a comprehensive (and comprehensible) introduction to the two fundamental algorithms in deep learning: gradient descent and backpropagation. Finally, Kelleher considers the future of deep learning—major trends, possible developments, and significant challenges.