Parametri
- 544pagine
- 20 ore di lettura
Maggiori informazioni sul libro
This authoritative and accessible treatment of deep learning strikes a pragmatic balance between theory and practice. As a fast-evolving field with significant relevance in today's digital landscape, it covers essential topics, recent advancements, and cutting-edge concepts. Unlike many texts that overwhelm with technical details, Simon Prince curates only the most critical ideas, presenting them in an intuitive and digestible manner. Concepts range from machine learning basics to advanced models, explained in lay terms and detailed mathematically, complemented by visual illustrations. The textbook is self-contained and suitable for anyone with a basic understanding of applied mathematics. It includes up-to-date discussions on topics like transformers and diffusion models, with short, focused chapters that gradually increase in complexity to help students grasp challenging concepts. The pragmatic approach provides the necessary detail for implementing basic model versions, while the streamlined presentation distinguishes essential ideas from extraneous context. With minimal mathematical prerequisites, extensive illustrations, and practice problems, the material is made widely accessible. Additionally, programming exercises are provided in accompanying Python Notebooks.
Acquisto del libro
Understanding Deep Learning, Simon J. D. Prince
- Lingua
- Pubblicato
- 2023
Metodi di pagamento
Ancora nessuna valutazione.
- Titolo
- Understanding Deep Learning
- Lingua
- Inglese
- Autori
- Simon J. D. Prince
- Editore
- MIT Press
- Pubblicato
- 2023
- Pagine
- 544
- ISBN10
- 0262048647
- ISBN13
- 9780262048644
- Serie
- Tag
- Saggistica, Tecnologia & Ingegneria, Scienza e Matematica, Computer & Internet, Intelligenza artificiale, Apprendimento Automatico
- Descrizione
- This authoritative and accessible treatment of deep learning strikes a pragmatic balance between theory and practice. As a fast-evolving field with significant relevance in today's digital landscape, it covers essential topics, recent advancements, and cutting-edge concepts. Unlike many texts that overwhelm with technical details, Simon Prince curates only the most critical ideas, presenting them in an intuitive and digestible manner. Concepts range from machine learning basics to advanced models, explained in lay terms and detailed mathematically, complemented by visual illustrations. The textbook is self-contained and suitable for anyone with a basic understanding of applied mathematics. It includes up-to-date discussions on topics like transformers and diffusion models, with short, focused chapters that gradually increase in complexity to help students grasp challenging concepts. The pragmatic approach provides the necessary detail for implementing basic model versions, while the streamlined presentation distinguishes essential ideas from extraneous context. With minimal mathematical prerequisites, extensive illustrations, and practice problems, the material is made widely accessible. Additionally, programming exercises are provided in accompanying Python Notebooks.