Chapter 1, Revisiting Deep Learning Architecture and Techniques, provides an overview of the deep learning techniques that are covered in this book.
Chapter 2, Deep Neural Networks for Multiclass Classification, covers the necessary steps to apply deep learning neural networks to binary and multiclass classification problems. The steps are illustrated using a churn dataset and include data preparation, one-hot encoding, model fitting, model evaluation, and prediction.
Chapter 3, Deep Neural Networks for Regression, illustrates how to develop a prediction model for numeric response. Using the Boston Housing example, this chapter introduces the steps for data preparation, model creation, model fitting, model evaluation, and prediction.
Chapter 4, Image Classification and Recognition, illustrates the use of deep learning neural networks for image classification and recognition using the Keras package with the help of an easy-to-follow example. The steps involved include exploring image data, resizing and reshaping images, one-hot encoding, developing a sequential model, compiling the model, fitting the model, evaluating the model, prediction, and model performance assessment using a confusion matrix.
Chapter 5, Image Classification Using Convolutional Neural Networks, introduces the steps for applying image classification and recognition using convolutional neural networks (CNNs) with an easy-to-follow practical example. CNN is a popular deep neural network and is considered the 'gold standard' for large-scale image classification.
Chapter 6, Applying Autoencoder Neural Networks Using Keras, goes over the steps for applying autoencoder neural networks using Keras. The practical example used illustrates the steps for taking images as input, training them with an autoencoder, and finally, reconstructing images.
Chapter 7, Image Classification for Small Data Using Transfer Learning, illustrates the application of transfer learning to NLP. The steps involved include data preparation, defining a deep neural network model in Keras, training the model, and model assessment.
Chapter 8, Creating New Images Using Generative Adversarial Networks, illustrates the application of generative adversarial networks (GANs) to generate new images using a practical example. The steps for image classification include image data preprocessing, feature extraction, developing an RBM model, and model performance assessment.
Chapter 9, Deep Network for Text Classification, provides the steps for applying text classification using deep neural networks and illustrates the process with an easy-to-follow example. Text data, such as customer comments, product reviews, and movie reviews, play an important role in business, and text classification is an important deep learning problem.
Chapter 10, Text Classification Using Recurrent Neural Networks, provides the steps for applying recurrent neural networks to an image classification problem with the help of a practical example. The steps covered include data preparation, defining the recurrent neural network model, training, and finally, the evaluation of the model performance.
Chapter 11 , Text Classification Using a Long Short-Term Memory Network, illustrates the steps for using a long short-term memory (LSTM) neural network for sentiment classification. The steps involved include text data preparation, creating an LSTM model, training the model, and assessing the model.
Chapter 12, Text Classification Using Convolutional Recurrent Networks, illustrates the application of recurrent convolutional networks for news classification. The steps involved include text data preparation, defining a recurrent convolutional network model in Keras, training the model, and model assessment.
Chapter 13, Tips, Tricks, and the Road Ahead, discusses the road ahead in terms of putting deep learning into action and best practices.
