Chapter 1, Overview of TensorFlow and Machine Learning, explains the basics of TensorFlow and has you build a machine learning model using logistic regression to classify hand-written digits.
Chapter 2, Using Machine Learning to Detect Exoplanets in Outer Space, covers how to detect exoplanets in outer space using ensemble methods that are based on decision trees.
Chapter 3, Sentiment Analysis in Your Browser Using TensorFlow.js, explains how to train and build a model on your web browser using TensorFlow.js. We will build a sentiment analysis model using a movie reviews dataset and deploy it to your web browser for making predictions.
Chapter 4, Digit Classification Using TensorFlow Lite, focuses on building a deep learning model for classifying hand-written digits and converting them into a mobile-friendly format using TensorFlow Lite. We will also learn about the architecture of TensorFlow Lite and how to use TensorBoard for visualizing neural networks.
Chapter 5, Speech to Text and Topic Extraction Using NLP, focuses on learning about various options for speech-to-text and pre-built models by Google in TensorFlow using the Google Speech Command dataset.
Chapter 6, Predicting Stock Prices using Gaussian Process Regression, explains a popular forecasting model called a Gaussian process in Bayesian statistics. We use Gaussian processes from a GpFlow library built on top of TensorFlow to develop a stock price prediction model.
Chapter 7, Credit Card Fraud Detection Using Autoencoders, introduces a dimensionality reduction technique called autoencoders. We identify fraudulent transactions in a credit card dataset by building autoencoders using TensorFlow and Keras.
Chapter 8, Generating Uncertainty in Traffic Signs Classifier using Bayesian Neural Networks, explains Bayesian neural networks, which help us to quantify the uncertainty in predictions. We will build a Bayesian neural network using TensorFlow to classify German traffic signs.
Chapter 9, Generating Matching Shoe Bags from Shoe Images Using DiscoGANs, introduces a new type of GAN known as Discovery GANs (DiscoGANs). We understand how its architecture differs from standard GANs and how it can be used in style transfer problems. Finally, we build a DiscoGAN model in TensorFlow to generate matching shoe bags from shoe images, and vice versa.
Chapter 10, Classifying Clothing Images Using Capsule Networks, implements a very recent image classification model—Capsule Networks. We get to understand its architecture and explain the nuances of its implementation in TensorFlow. We use the Fashion MNIST dataset to classify clothing images using this model.
Chapter 11, Making Quality Product Recommendations Using TensorFlow, covers techniques such as matrix factorization (SVD++), learning to rank, and convolutional neural network variations for recommendation tasks with TensorFlow.
Chapter 12, Object Detection at a Large Scale with TensorFlow, explores Yahoo's TensorFlowOnSpark framework for distributed deep learning on Spark clusters. Then, we will apply TensorFlowOnSpark to a large-scale dataset of images and train the network to detect objects.
Chapter 13, Generating Book Scripts Using LSTMs, explains how LSTMs are useful in generating new text. We use a book script from one of Packt's published books to bsuild an LSTM-based deep learning model that can generate book scripts on its own.
Chapter 14, Playing Pacman Using Deep Reinforcement Learning, explains the utilization of reinforcement learning for training a model to play Pacman, teaching you about reinforcement learning in the process.
Chapter 15, What is Next?, introduces the other components of the TensorFlow ecosystem that are useful for deploying the models in production. We will also learn about various applications of AI across industries, the limitations of deep learning, and ethics in AI.
