Bernhard Mehlig is Professor in Physics at the University of Gothenburg, Sweden. His research is focused on statistical physics of complex systems, and he has published extensively in this area. In 2010, he was awarded the prestigious Göran Gustafsson prize in physics for his outstanding research in statistical physics. He has taught a course on machine learning for more than 15 years at the University of Gothenburg.

• 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.

'… 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