What this book covers
Chapter 1, Introduction to Deep Learning with KNIME Analytics Platform, is a preparation chapter to get you familiar with the tool and the recent popularity of deep learning techniques.
Chapter 2, Data Access and Preprocessing with KNIME Analytics Platform, dives a bit deeper into the basic and advanced functionalities of KNIME Analytics Platform: from data access to workflow parameterization.
Chapter 3, Getting Started with Neural Networks, is the only theoretical chapter of the book. It paints an overview of the basic concepts around neural and deep learning networks and the algorithms used to train them.
Chapter 4, Building and Training a Feedforward Neural Network, is where we put into practice what we describe in Chapter 3, Getting Started with Neural Networks; we will build, train, and evaluate our first simple feedforward networks for classification tasks.
Chapter 5, Autoencoder for Fraud Detection, is where, with a neural autoencoder to solve the problem of fraud detection in credit card transactions, we start the series of case studies based on deep learning solutions.
Chapter 6, Recurrent Neural Networks for Demand Prediction, is where we introduce Long Short-Term Memory (LSTM) models in recurrent neural networks. Indeed, with their dynamic behavior, they are particularly effective in solving time series problems, such as a classic demand prediction problem.
Chapter 7, Implementing NLP Applications, covers how LSTM-based recurrent neural networks are often also used to implement solutions for natural language processing tasks. In this chapter, we cover a few case studies for free text generation, free name generation, and sentiment analysis.
Chapter 8, Neural Machine Translation, looks at an encoder-decoder architecture for automatic translations.
Chapter 9, Convolutional Neural Networks for Image Classification, covers a case study on image classification, which we could not miss. We classify histopathology images into cancer diagnoses using a convolutional neural network.
Chapter 10, Deploying a Deep Learning Network, starts describing the deployment phase. A simple example of the deployment workflow is explained in detail.
Chapter 11, Best Practices and Other Deployment Options, extends the previous chapter dedicated to deployment with more deployment options, such as web applications and REST services, and we conclude the book with a few tips and tricks.