Praise for AI and Machine Learning for Coders “Machine learning should be in the toolbox of every great engineer in this coming decade. For people looking to get started, AI and Machine Learning for Coders by Laurence Moroney is the much-needed practical starting point to dive deep into deep learning, computer vision, and NLP.” —Dominic Monn, Machine Learning at Doist “The book is a great introduction to understand and practice machine learning and artificial intelligence models by using TensorFlow. It covers various deep learning models, and their practical applications, as well as how to utilize TensorFlow framework to develop and deploy ML/AI applications across platforms. I recommend it for anyone who is interested in ML and AI practice.” —Jialin Huang PhD, Data and Applied Scientist at Microsoft “Laurence’s book helped me refresh TensorFlow framework and Coursera Specialization, and motivated me to take the certification provided by Google. If you have time and you are willing to embark to an ML journey, this book is a starting point from the practice side.” —Laura Uzcátegui, Software Engineer “This book is a must-read for developers who would like to get into AI/ML. You will learn a variety of examples by coding instead of math equations.” —Margaret Maynard-Reid, ML Google Developer Expert “A practical handbook to have on your desk for implementing deep learning models.” —Pin-Yu Chen, Research Staff Member at IBM Research AI “A fun book to read and practice coding for AI and machine learning projects. Intuitive wording and graphs to explain the nonintuitive concepts and algorithms. Cool coding examples to teach you key building blocks for AI and ML. In the end, you can code AI projects for your PC program, Android, iOS and Browser!” —Su Fu, CEO of Alchemist 1. Foreword 2. Preface a. Who Should Read This Book b. Why I Wrote This Book c. Navigating This Book d. Technology You Need to Understand e. Online Resources f. Conventions Used in This Book g. Using Code Examples h. O’Reilly Online Learning i. How to Contact Us j. Acknowledgments 3. I. Building Models 4. 1. Introduction to TensorFlow a. What Is Machine Learning? b. Limitations of Traditional Programming c. From Programming to Learning d. What Is TensorFlow? e. Using TensorFlow i. Installing TensorFlow in Python ii. Using TensorFlow in PyCharm iii. Using TensorFlow in Google Colab f. Getting Started with Machine Learning i. Seeing What the Network Learned g. Summary 5. 2. Introduction to Computer Vision a. Recognizing Clothing Items i. The Data: Fashion MNIST b. Neurons for Vision c. Designing the Neural Network i. The Complete Code d. Training the Neural Network e. Exploring the Model Output f. Training for Longer—Discovering Overfitting g. Stopping Training h. Summary 6. 3. Going Beyond the Basics: Detecting Features in Images a. Convolutions b. Pooling c. Implementing Convolutional Neural Networks d. Exploring the Convolutional Network e. Building a CNN to Distinguish Between Horses and Humans i. The Horses or Humans Dataset ii. The Keras ImageDataGenerator iii. CNN Architecture for Horses or Humans iv. Adding Validation to the Horses or Humans Dataset v. Testing Horse or Human Images f. Image Augmentation g. Transfer Learning h. Multiclass Classification i. Dropout Regularization j. Summary 7. 4. Using Public Datasets with TensorFlow Datasets a. Getting Started with TFDS b. Using TFDS with Keras Models i. Loading Specific Versions c. Using Mapping Functions for Augmentation i. Using TensorFlow Addons d. Using Custom Splits e. Understanding TFRecord f. The ETL Process for Managing Data in TensorFlow i. Optimizing the Load Phase ii. Parallelizing ETL to Improve Training Performance g. Summary 8. 5. Introduction to Natural Language Processing a. Encoding Language into Numbers i. Getting Started with Tokenization ii. Turning Sentences into Sequences b. Removing Stopwords and Cleaning Text c. Working with Real Data Sources i. Getting Text from TensorFlow Datasets ii. Getting Text from CSV Files iii. Getting Text from JSON Files d. Summary 9. 6. Making Sentiment Programmable Using Embeddings a. Establishing Meaning from Words i. A Simple Example: Positives and Negatives ii. Going a Little Deeper: Vectors b. Embeddings in TensorFlow i. Building a Sarcasm Detector Using Embeddings ii. Reducing Overfitting in Language Models iii. Using the Model to Classify a Sentence c. Visualizing the Embeddings d. Using Pretrained Embeddings from TensorFlow Hub e. Summary 10. 7. Recurrent Neural Networks for Natural Language Processing a. The Basis of Recurrence b. Extending Recurrence for Language c. Creating a Text Classifier with RNNs i. Stacking LSTMs d. Using Pretrained Embeddings with RNNs e. Summary 11. 8. Using TensorFlow to Create Text a. Turning Sequences into Input Sequences b. Creating the Model c. Generating Text i. Predicting the Next Word ii. Compounding Predictions to Generate Text d. Extending the Dataset e. Changing the Model Architecture f. Improving the Data g. Character-Based Encoding h. Summary 12. 9. Understanding Sequence and Time Series Data a. Common Attributes of Time Series i. Trend ii. Seasonality iii. Autocorrelation iv. Noise b. Techniques for Predicting Time Series i. Naive Prediction to Create a Baseline ii. Measuring Prediction Accuracy iii. Less Naive: Using Moving Average for Prediction iv. Improving the Moving Average Analysis c. Summary 13. 10. Creating ML Models to Predict Sequences a. Creating a Windowed Dataset i. Creating a Windowed Version of the Time Series Dataset b. Creating and Training a DNN to Fit the Sequence Data c. Evaluating the Results of the DNN d. Exploring the Overall Prediction e. Tuning the Learning Rate f. Exploring Hyperparameter Tuning with Keras Tuner g. Summary 14. 11. Using Convolutional and Recurrent Methods for Sequence Models a. Convolutions for Sequence Data i. Coding Convolutions ii. Experimenting with the Conv1D Hyperparameters b. Using NASA Weather Data i. Reading GISS Data in Python c. Using RNNs for Sequence Modeling i. Exploring a Larger Dataset d. Using Other Recurrent Methods e. Using Dropout f. Using Bidirectional RNNs g. Summary 15. II. Using Models 16. 12. An Introduction to TensorFlow Lite a. What Is TensorFlow Lite?