Deep learning in science

This is the first rigorous, self-contained treatment of the theory of deep learning. Starting with the foundations of the theory and building it up, this is essential reading for any scientists, instructors, and students interested in artificial intelligence and deep learning. It provides guidance on how to think about scientific questions, and leads readers through the history of the field and its fundamental connections to neuroscience. The author discusses many applications to beautiful problems in the natural sciences, in physics, chemistry, and biomedicine. Examples include the search for exotic particles and dark matter in experimental physics, the prediction of molecular properties and reaction outcomes in chemistry, and the prediction of protein structures and the diagnostic analysis of biomedical images in the natural sciences. The text is accompanied by a full set of exercises at different difficulty levels and encourages out-of-the-box thinking.

Machine generated contents note: 1.1.Carbon-Based and Silicon-Based Computing -- 1.2.Early Beginnings Until the Late 1940s -- 1.3.From 1950 to 1980 -- 1.4.From 1980 to Today -- 1.5.Roadmap -- 1.6.Exercises -- 2.1.Synapses -- 2.2.Units or Neurons -- 2.3.Activations -- 2.4.Transfer Functions -- 2.5.Discrete versus Continuous Time -- 2.6.Networks and Architectures -- 2.7.Functional and Cardinal Capacity of Architectures -- 2.8.The Bayesian Statistical Framework -- 2.9.Information Theory -- 2.10.Data and Learning Settings -- 2.11.Learning Rules -- 2.12.Computational Complexity Theory -- 2.13.Exercises -- 3.1.Supervised Shallow Networks and their Design -- 3.2.Capacity of Shallow Networks -- 3.3.Shallow Learning -- 3.4.Extensions of Shallow Learning -- 3.5.Exercises -- 4.1.Functional Capacity -- 4.2.Universal Approximation Properties -- 4.3.The Capacity of A(n, m, 1) Architectures -- 4.4.Exercises -- 5.1.A General Autoencoder Framework -- 5.2.General Autoencoder Properties -- 5.3.Linear Autoencoders -- 5.4.Non-Linear Autoencoders: Unrestricted Boolean Case -- 5.5.Other Autoencoders and Autoencoder Properties -- 5.6.Exercises -- 6.1.Why Deep? -- 6.2.Functional Capacity: Deep Linear Case…