Machine Learning with Neural Networks
An Introduction for Scientists and Engineers

Modern introduction to machine learning with neural networks. Key principles of the topic are described alongside cutting-edge applications.

Bernhard Mehlig (Author)

9781108494939, Cambridge University Press

Hardback, published 28 October 2021

260 pages
25 x 17.4 x 1.6 cm, 0.66 kg

'… for someone who wants to understand neural networks at a fundamental level, or to code something from scratch, or to make some advances in the core ideas and develop the field as a result, then this book will give you the theoretical framework for doing just that.' Matt Probert, Contemporary Physics

This modern and self-contained book offers a clear and accessible introduction to the important topic of machine learning with neural networks. In addition to describing the mathematical principles of the topic, and its historical evolution, strong connections are drawn with underlying methods from statistical physics and current applications within science and engineering. Closely based around a well-established undergraduate course, this pedagogical text provides a solid understanding of the key aspects of modern machine learning with artificial neural networks, for students in physics, mathematics, and engineering. Numerous exercises expand and reinforce key concepts within the book and allow students to hone their programming skills. Frequent references to current research develop a detailed perspective on the state-of-the-art in machine learning research.

Acknowledgements. 1. Introduction. Part I. Hopfield Networks: 2. Deterministic Hopfield networks
3. Stochastic Hopfield networks
4. The Boltzmann distribution. Part II. Supervised Learning: 5. Perceptrons
6. Stochastic gradient descent
7. Deep learning
8. Convolutional networks
9. Supervised recurrent networks. Part III. Learning Without Labels: 10. Unsupervised learning
11. Reinforcement learning. Bibliography. Author Index. Index.

Subject Areas: Neural networks & fuzzy systems [UYQN], Machine learning [UYQM], Statistical physics [PHS]