Deep learning using Python

Table of content 1. Fundamentals of Neural Networks 1.1 Introduction 1.2 Types of Machine Learning 1.3 Overview of Artificial Neural Networks 2. Convolutional Neural Network 2.1 Introduction 2.2 Components of CNN Architecture 2.3 Rectified Linear Unit (ReLU) Layer 2.4 Exponential Linear Unit (ELU, or SELU) 2.5 Unique Properties of CNN 2.6 Architectures of CNN 2.7 Applications of CNN 3. Recurrent Neural Network: Basic Concepts 3.1 Introduction 3.2 Simple Recurrent Neural Network 3.3 LSTM Implementation 3.4 Gated Recurrent Unit (GRU) 3.5 Deep Recurrent Neural Network 4. Autoencoder 4.1 Introduction 4.2 Features of Autoencoder 4.3 Types of Autoencoder 5. Restricted Boltzmann Machine 5.1 Boltzmann Machine 5.2 RBM Architecture 5.3 Example 5.4 Types of RBM 6. Open-Source Frameworks for Deep Learning 6.1 Python - An Introduction 6.2 Environmental Setup 6.3 Deep Learning with Python 6.4 Scientific Python (SciPy) 6.5 Frameworks 6.6 Hardware Support for Deep Learning 7. Applications of Deep Learning 7.1 Introduction 7.2 Image Classification Using CNN 7.3 Visual Speech Recognition Using 3D-CNN 7.4 Stock Market Prediction Using Recurrent Neural Network 7.5 Next-Word Prediction Using RNN-LSTM 7.6 Tamil Handwritten Character Optical Recognition Using CRNN 7.7 Future Scope Summary Review Questions Assignment Problems References

The book has been divided into seven chapters. Chapter 1 elaborately deals with the fundamentals of deep learning, to enable any reader to understand the deep learning architectures elaborated in subsequent chapters. Chapter 2 deals with Convolutional Neural Networks (CNNs), which have proven to be very effective in the area of computer vision. Chapter 3 deals with Recurrent Neural Networks (RNNs) and its variants. The various types of autoencoders, which are a type of Artificial Neural Network used to learn efficient data encoding, are presented in Chapter 4. To learn the probability distribution over the set of inputs, Restricted Boltzmann Machine (RBM) is discussed in Chapter 5. Chapter 6 presents popular open source frameworks in Python for deep learning applications. Chapter 7 describes how to utilize the knowledge that you have gained from previous chapters in real-time applications.