Deep Learning - Glassner, Andrew

. .

Résumé :
Ever since computers began beating us at chess, they've been getting better at a wide range of human activities, from writing songs and generating news articles to helping doctors diagnose and treat diseases. Deep learning is the source of many of these breakthroughs, and its remarkable ability to find patterns in data has made it the fastest-growing field in artificial intelligence. Digital phone assistants use deep learning to understand and respond to voice commands . automotive systems use it to safely navigate roads . and online platforms use it to make personalized recommendations for movies and books. Deep Learning will help you understand this fascinating field without requiring any advanced math or programming skills. The book's conversational style, full-color illustrations, and real-world examples expertly explain key concepts. If you want to know how deep learning tools work and use them yourself, you'll find the answers here. And when you're ready to write your own programs, the supplemental Python notebooks in the book's GitHub repository will get you started. You'll learn how : - Text generators create stories and articles . - Deep learning systems learn to win human games . - Image classification systems identify objects or people in a photo . - Probabilities are useful in everyday life . - Machine learning techniques contribute to modern Al Intellectual adventurers of all kinds can use the powerful ideas covered in Deep Learning to build intelligent systems that help us better understand the world around us. It's the future of Al, and this book will take you there.

Biographie:
Dr. Andrew GLASSNER is a Senior Research Scientist at Weta Digital, where he uses deep learning to help artists produce visual effects for film and television. He was Technical Papers Chair for SIGGRAPH '94, founding editor of the Journal of Computer Graphics Tools, and editor-in-chief of ACM Transactions on Graphics. His prior books include the Graphics Gems series and the textbook Principles of Digital Image Synthesis.

Sommaire:
Part I: Foundational Ideas
1. An Overview of Machine Learning Techniques
2. Essential Statistical Ideas
3. Probability
4. Bayes' Rule
5. Curves and Surfaces
6. Information Theory
Part II: Basic Machine Learning
7. Classification
8. Training and Testing
9. Overfitting and Underfitting
10. Data Preparation
11. Classifiers
12. Ensembles
Part III: Deep Learning Basics
13. Neural Networks
14. Backpropagation
15. Optimizers
Part IV: Beyond the Basics
16. Convolutional Neural Networks
17. Convnets in Practice
18. Recurrent Neural Networks
19. Autoencoders
20. Reinforcement Learning
21. Generative Adversarial Networks
22. Creative Applications
Index