An introductory book on a wide range of deep learning topics, covering the mathematical and conceptual background, deep learning techniques used in the field, and research prospects.

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world as a hierarchy of concepts. Because the computer accumulates knowledge from experience, there is no need for all the knowledge required by the computer to be meticulously defined by a human operator. The hierarchy of concepts allows the computer to learn complex ideas by building them from simpler ones — a graph of such hierarchies would have several levels of depth. This book presents a wide range of topics in deep learning.

This book can be used by undergraduate or graduate students who wish to pursue either a professional or research career, as well as by software engineers who want to begin using deep learning in their products or platforms. It is accompanied by a website with supplementary material for both readers and instructors.

Contents:

• Basic concepts of applied mathematics and machine learning
• Linear algebra
• Probability and information theory
• Numerical computations
• Basic concepts of machine learning
• Deep feedforward networks
• Regularization for deep learning
• Optimization for training deep models
• Convolutional networks
• Practical methodologies
• Applications
• Linear factor models
• Autoencoders
• Representation learning
• Structured probabilistic models for deep learning
• Monte Carlo methods
• Addressing the partition function
• Approximate inference
• Deep generative models