deep learning

Written by three experts in the field, "Deep Learning" is the only comprehensive book on this topic. Deep Learning is a form of machine learning that enables computers to learn from experiences and understand the world in the form of a hierarchy of concepts. As the computer gathers knowledge from experiences, it is not necessary for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complex concepts by building them from simpler ones; a diagram of these hierarchies would be many layers deep. This book introduces a wide range of topics in Deep Learning. The text provides mathematical and conceptual foundations and covers relevant concepts from linear algebra, probability theory, information theory, numerical computations, and machine learning. It describes Deep Learning techniques used by practitioners in the industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it provides an overview of applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and video games. Finally, the book offers research perspectives and addresses theoretical topics such as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. "Deep Learning" can be utilized by undergraduate or graduate students pursuing careers in industry or research, as well as by software engineers looking to start using Deep Learning in their products or platforms. A website provides additional material for readers and instructors.