Chapter 1, Machine Learning and Neural Networks 101, covers the basics of machine learning and neural networks. The first chapter aims to solidify your understanding of machine learning and neural networks. To do that, we'll create our own neural network from scratch in Python, without any machine learning libraries.
Chapter 2, Predicting Diabetes with Multilayer Perceptrons, kick-starts our first neural network project. Using a basic neural network known as a multilayer perceptron, we'll build a classifier that can predict whether a patient is at risk of diabetes.
Chapter 3, Predicting Taxi Fares with Deep Feedforward Nets, makes use of a deep feedforward neural network in a regression problem. In particular, we'll use a neural network to predict taxi fares in New York City.
Chapter 4, Cats Versus Dogs – Image Classification Using CNNs, uses a convolutional neural network (CNN) for an image classification problem. We'll use the CNN to predict whether an image includes a cat or a dog.
Chapter 5, Removing Noise from Images Using Autoencoders, leverages on autoencoders for noise removal in images. The images come from office documents corrupted by coffee stains and other artifacts. We'll use autoencoders to remove these artifacts from the images, restoring them to their original state.
Chapter 6, Sentiment Analysis on Movie Reviews Using LSTM, uses a long short-term memory (LSTM) neural network to analyze and classify the sentiment of movie reviews posted online. We'll create an LSTM neural network that is able to discern the sentiment of written English sentences.
Chapter 7, Implementing a Face Recognition System with Neural Networks, uses a Siamese neural network to build a facial recognition system that can recognize our own faces, using the webcam in our laptop.
Chapter 8, What's Next?, summarizes everything that we have learned in this book. We'll peer ahead into the future and see what machine learning and AI will look like in the next few years.
