Title
Artificial Intelligence Engines: A Tutorial Introduction To The Mathematics Of Deep Learning
Processing time: 1-3 days
US Orders Ships in: 3-5 days
International Orders Ships in: 8-12 days
Return Policy: 15-days return on defective items
Payment Option
Authoritative, Funny, And Concise Steven Strogatz, Professor Of Applied Mathematics, Cornell University.The Brain Has Always Had A Fundamental Advantage Over Conventional Computers: It Can Learn. However, A New Generation Of Artificial Intelligence Algorithms, In The Form Of Deep Neural Networks, Is Rapidly Eliminating That Advantage. Deep Neural Networks Rely On Adaptive Algorithms To Master A Wide Variety Of Tasks, Including Cancer Diagnosis, Object Recognition, Speech Recognition, Robotic Control, Chess, Poker, Backgammon And Go, At Superhuman Levels Of Performance. In This Richly Illustrated Book, Key Neural Network Learning Algorithms Are Explained Informally First, Followed By Detailed Mathematical Analyses. Topics Include Both Historically Important Neural Networks (Perceptrons, Hopfield Nets, Boltzmann Machines And Backpropagation Networks), And Modern Deep Neural Networks (Variational Autoencoders, Convolutional Networks, Generative Adversarial Networks, And Reinforcement Learning Using Sarsa And Qlearning). Online Computer Programs, Collated From Open Source Repositories, Give Handson Experience Of Neural Networks, And Powerpoint Slides Provide Support For Teaching. Written In An Informal Style, With A Comprehensive Glossary, Tutorial Appendices (E.G. Bayes' Theorem, Maximum Likelihood Estimation), And A List Of Further Readings, This Is An Ideal Introduction To The Algorithmic Engines Of Modern Artificial Intelligence.Dr James V Stone Is An Honorary Associate Professor At The University Of Sheffield, England.
⚠️ WARNING (California Proposition 65):
This product may contain chemicals known to the State of California to cause cancer, birth defects, or other reproductive harm.
For more information, please visit www.P65Warnings.ca.gov.
- Q: How many pages does this book have? A: This book has two hundred sixteen pages. It's a comprehensive guide to the mathematics of deep learning.
- Q: What is the binding type of this book? A: The binding type is paperback. This makes it lightweight and easy to carry.
- Q: What are the dimensions of this book? A: The dimensions are six inches in length, zero point forty-nine inches in width, and nine point zero two inches in height. These measurements make it a convenient size for reading.
- Q: How do I use the concepts in this book? A: You can apply the concepts by following the illustrated explanations and examples provided. It’s designed for readers to gain hands-on experience with neural networks.
- Q: Is this book suitable for beginners? A: Yes, this book is suitable for beginners. It explains complex topics in an informal style that is easy to understand.
- Q: What age group is this book appropriate for? A: This book is appropriate for adults and older teenagers interested in artificial intelligence. It covers advanced topics in mathematics.
- Q: How should I store this book? A: Store this book in a cool, dry place away from direct sunlight. This will help maintain its condition over time.
- Q: Can I clean the book if it gets dirty? A: Yes, you can clean the book gently with a soft, dry cloth. Avoid using water or cleaning agents.
- Q: Does this book contain any safety warnings? A: No, this book does not contain safety warnings. It is focused on educational content about artificial intelligence.
- Q: How does this book compare to other AI texts? A: This book stands out due to its humorous and concise explanations of deep learning. It also includes practical examples and online programs.
- Q: Is this book good for advanced learners? A: Yes, advanced learners can benefit from this book. It covers both historical and modern neural networks in detail.
- Q: What if I receive a damaged book? A: If you receive a damaged book, you should contact the seller for a replacement or refund. Most sellers have return policies in place.
- Q: Is there an online component to this book? A: Yes, the book includes online computer programs for hands-on experience with neural networks. These programs are collated from open source repositories.
- Q: What should I do if I have questions while reading? A: You can refer to the comprehensive glossary and tutorial appendices provided in the book for clarification on complex topics.
- Q: Can I use this book for teaching purposes? A: Yes, this book is suitable for teaching purposes as it includes PowerPoint slides for support. It is designed for educational use.