TensorFlow 2 Pocket Primer (Computing)

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 info@merclearning.com. 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) Cover Title Copyright Dedication Contents Preface What Is the Goal? What Will I Learn from This Book? The TF 1.x and TF 2.0 Books: How Are They Different? Why Isn’t Keras in Its Own Chapter in This Book? How Much Keras Knowledge Is Needed for This Book? Do I Need to Learn the Theory Portions of This Book? How Were the Code Samples Created What Are the Technical Prerequisites for This Book? What Are the Nontechnical Prerequisites for This Book? Which Topics Are Excluded? How Do I Set Up a Command Shell? Companion Files What Are the “Next Steps” after Finishing This Book? Chapter 1: Introduction to TensorFlow 2 What Is TF 2? TF 2 Use Cases TF 2 Architecture: The Short Version TF 2 Installation TF 2 and the Python REPL Other TF 2-Based Toolkits TF 2 Eager Execution TF 2 Tensors, Data Types, and Primitive Types TF 2 Data Types TF 2 Primitive Types Constants in TF 2 Variables in TF 2 The tf.rank() API The tf.shape() API Variables in TF 2 (Revisited) TF 2 Variables versus Tensors What Is @tf.function in TF 2? How Does @tf.function Work? A Caveat about @tf.function in TF 2 The tf.print() Function and Standard Error Working with @tf.function in TF 2 An Example without @tf.function An Example with @tf.function Overloading Functions with @tf.function What Is AutoGraph in TF 2? Arithmetic Operations in TF 2 Caveats for Arithmetic Operations in TF 2 TF 2 and Built-In Functions Calculating Trigonometric Values in TF Calculating Exponential Values in TF 2 Working with Strings in TF 2 Working with Tensors and Operations in TF 2 Second-Order Tensors in TF 2 (1) Second-Order Tensors in TF 2 (2) Multiplying Two Second-Order Tensors in TF Convert Python Arrays to TF Tensors Conflicting Types in TF 2 Differentiation and tf.GradientTape in TF 2 Examples of tf.GradientTape Using the watch() Method of tf.GradientTape Using Nested Loops with tf.GradientTape Other Tensors with tf.GradientTape A Persistent Gradient Tape Migrating TF 1.x Code to TF 2 Code (optional) Two Conversion Techniques from TF 1.x to TF 2 Converting to Pure TF 2 Functionality Converting Sessions to Functions Combine tf.data.Dataset and @tf.function Use Keras Layers and Models to Manage Variables The TensorFlow Upgrade Script (optional) Summary Chapter 2: Useful TF 2 APIs TF 2 Tensor Operations Using for Loops in TF 2 Using while Loops in TF 2 TF 2 Operations with Random Numbers TF 2 Tensors and Maximum Values The TF 2 range() API Operations with Nodes The tf.size(), tf.shape(), and tf.rank() APIs The tf.reduce_prod() and tf.reduce_sum() APIs The tf.reduce_mean() API The tf.random_normal() API (1) The TF 2 random_normal() API (2) The tf.truncated_normal() API The tf.reshape() API The tf.range() API The tf.equal() API (1) The tf.equal() API (2) The tf.argmax() API (1) The tf.argmax() API (2) The tf.argmax() API (3) Combining tf.argmax() and tf.equal() APIs Combining tf.argmax() and tf.equal() APIs (2) The tf.map_fn() API What Is a One-Hot Encoding? The TF one_hot() API Other Useful TF 2 APIs Save and Restore TF 2 Variables TensorFlow Ragged Constants and Tensors What Is a TFRecord? A Simple TFRecord What Are tf.layers? What Is TensorBoard? TF 2 with TensorBoard TensorBoard Dashboards The tf.summary API Google Colaboratory Other Cloud Platforms Gcp Sdk Summary Chapter 3: TF2 Datasets The TF 2 tf.data.Datasets Creating a Pipeline Basic Steps for TF 2 Datasets A Simple TF 2 tf.data.Dataset What Are Lambda Expressions? Working with Generators in TF 2 What Are Iterators? (optional) TF 1.x Iterators (optional) Concatenating TF 2 tf.Data.Datasets The TF 2 reduce() Operator Working with Generators in TF 2 The TF 2 filter() Operator (1) The TF 2 filter() Operator (2) The TF 2 batch() Operator (1) The TF 2 batch() Operator (2) The TF 2 map() Operator (1) The TF 2 map() Operator (2) The TF 2 flatmap() Operator (1) The TF 2 flatmap() Operator (2) The TF 2 flat_map() and filter() Operators The TF 2 repeat() Operator The TF 2 take() Operator Combining the TF 2 map() and take() Operators Combining the TF 2 zip() and batch() Operators Combining the TF 2 zip() and take() Operators TF 2 tf.data.Datasets and Random Numbers TF 2, MNIST, and tf.data.Dataset Working with the TFDS Package in TF 2 The CIFAR10 Dataset and TFDS in TF 2 Working with tf.estimator What Are TF 2 Estimators? Other TF 2 Namespaces Summary Chapter 4: Linear Regression What Is Linear Regression? Linear Regression versus Curve-Fitting What Is Multivariate Analysis? When Are Solutions Exact in Machine Learning? Challenges with Linear Regression Nonlinear Data Nonconstant Variance of Error Terms Correlation of Error Terms Collinearity Outliers and Anomalies Other Types of Regression Working with Lines in the Plane Scatter Plots with NumPy and Matplotlib (1) Why the “Perturbation Technique” Is Useful Scatter Plots with NumPy and Matplotlib (2) A Quadratic Scatter Plot with NumPy and Matplotlib The Mean Squared Error (MSE) Formula A List of Error Types Nonlinear Least Squares What Is Regularization? Machine Learning and Feature Scaling Data Normalization vs. Standardization The Bias-Variance Trade-off Metrics for Measuring Models Limitations of R-Squared Confusion Matrix Accuracy vs. Precision vs. Recall Other Useful Statistical Terms What Is an F1 Score? What Is a p-value? Working with Datasets Training Data Versus Test Data What Is Cross-Validation? Calculating the MSE Manually Simple 2D Data Points in TF 2 TF2, tf.GradientTape(), and Linear Regression Working with Keras Working with Keras Namespaces in TF 2 Working with the tf.keras.layers Namespace Working with the tf.keras.activations Namespace Working with the tf.keras.datasets Namespace Working with the tf.keras.experimental Namespace Working with Other tf.keras Namespaces TF 2 Keras versus “Standalone” Keras Creating a Keras-Based Model Keras and Linear Regression Working with tf.estimator Summary Chapter 5: Working with Classifiers What Is Classification? What Are Classifiers? Common Classifiers What Are Linear Classifiers? What Is KNN? How to Handle a Tie in kNN What Are Decision Trees? What Are Random Forests? What Are SVMS? Trade-offs of SVMs What Is Bayesian Inference? Bayes’s Theorem Some Bayesian Terminology What Is MAP? Why Use Bayes’s Theorem? What Is a Bayesian Classifier? Types of Naive Bayes Classifiers Training Classifiers Evaluating Classifiers What Are Activation Functions? Why Do We Need Activation Functions? How Do Activation Functions Work? Common Activation Functions Activation Functions in Python The ReLU and ELU Activation Functions The Advantages and Disadvantages of ReLU ELU Sigmoid, Softmax, and Hardmax Similarities Softmax Softplus Tanh Sigmoid, Softmax, and Hardmax Differences TF 2 and the Sigmoid Activation Function What Is Logistic Regression? Setting a Threshold Value Logistic Regression: Assumptions Linearly Separable Data TensorFlow and Logistic Regression Keras and Early Stopping (1) Keras and Early Stopping (2) Keras and Metrics Distributed Training in TF 2 (Optional) Using tf.distribute.Strategy with Keras Summary Appendix: TF 2, Keras, and Advanced Topics What Is Deep Learning? What Are Hyperparameters? Deep Learning Architectures Problems That Deep Learning Can Solve Challenges in Deep Learning What Are Perceptrons? Definition of the Perceptron Function A Detailed View of a Perceptron The Anatomy of an Artificial Neural Network (ANN) The Model Initialization Hyperparameters The Activation Hyperparameter The Cost Function Hyperparameter The Optimizer Hyperparameter The Learning Rate Hyperparameter The Dropout Rate Hyperparameter What Is Backward Error Propagation? What Is a Multilayer Perceptron (MLP)? Activation Functions How Are Data Points Correctly Classified? Keras and the XOR Function A High-Level View of CNNs A Minimalistic CNN The Convolutional Layer (Conv2D) The ReLU Activation Function The Max Pooling Layer CNNs with Audio Signals CNNs and NLPs Displaying an Image in the MNIST Dataset Keras and the MNIST Dataset Keras, CNNs, and the MNIST Dataset What Is an RNN? Anatomy of an RNN What Is BPTT? Working with RNNs and TF 2 What Is an LSTM? Anatomy of an LSTM Bidirectional LSTMs LSTM Formulas LSTM Hyperparameter Tuning What Are GRUs? What Are Autoencoders? Autoencoders and PCA What Are Variational Autoencoders? What Are GANs? The VAE-GAN Model Working with NLP (Natural Language Processing) NLP Techniques The Transformer Architecture and NLP Transformer-XL Architecture NLP and Deep Learning NLP and Reinforcement Learning Data Preprocessing Tasks Popular NLP Algorithms What Is an n-Gram? What Is a Skip-Gram? What Is BoW? What Is Term Frequency? What Is Inverse Document Frequency (idf)? Untitled What Is tf-idf? What Are Word Embeddings? ELMo, ULMFit, OpenAI, and BERT What Is Translatotron? What Is Reinforcement Learning (RL)? What Are NFAs? What Are Markov Chains? Markov Decision Processes (MDPs) The Epsilon-Greedy Algorithm The Bellman Equation Other Important Concepts in RL RL Toolkits and Frameworks TF-Agents What Is Deep Reinforcement Learning (DRL)? Miscellaneous Topics TFX (TensorFlow Extended) TensorFlow Probability TensorFlow Graphics TF Privacy Summary 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 info@merclearning.com. **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 provides an overview of the major concepts to program using TensorFlow 2. The focus of this book is on basic programming instructions used in machine learning and deep learning. Includes companion files with source code (in Python) and figures. Features: Provides an overview of the most important TensorFlow programming techniques used for machine learning, deep learning, linear and logical regression, etc. Covers TensorFlow 2 and previous versions that run with TF2 Includes companion files with source code (in Python) and figures.