Rigorous treatment of the theory of deep learning from first principles, with applications to beautiful problems in the natural sciences.
Inhaltsverzeichnis
1. Introduction; 2. Basic Concepts; 3. Shallow Networks and Shallow Learning; 4. Two-Layer Networks and Universal Approximation; 5. Autoencoders; 6. Deep Networks and Backpropagation; 7. The Local Learning Principle; 8. The Deep Learning Channel; 9. Recurrent Networks; 10. Recursive Networks; 11. Applications in Physics; 12. Applications in Chemistry; 13. Applications in Biology and Medicine; 14. Conclusion; Appendix A. Reinforcement Learning and Deep Reinforcement Learning; Appendix B. Hints and Remarks for Selected Exercises; References; Index.