Read more
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.
List of contents
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.
About the author
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.
