Deep Learning

Viac o knihe

This book provides a thorough introduction to the fundamental concepts of deep learning, catering to both newcomers and seasoned professionals in machine learning. It addresses key ideas related to contemporary architectures and techniques, establishing a strong foundation for future specialization. As the field rapidly evolves, the focus is on enduring concepts. Organized into concise chapters, each one builds on the previous, making it ideal for a two-semester undergraduate or postgraduate course, while also being suitable for researchers and self-learners. A mathematical background is necessary, so the book includes a self-contained introduction to probability theory. However, it emphasizes clarity in understanding, prioritizing practical applications over abstract theory. Complex ideas are presented through various perspectives, including text, diagrams, mathematical formulas, and pseudo-code. Chris Bishop, a Technical Fellow at Microsoft and an esteemed figure in the field, along with Hugh Bishop, an Applied Scientist at Wayve, contribute their expertise. The book has been praised for its clarity and relevance, addressing the urgent need for a modern textbook in deep learning and AI, and anchoring its concepts in probability to reflect current industrial AI systems and future advancements toward artificial general intelligence.