Model Selection and Error Estimation in a Nutshell - Luca Oneto
-30% ar kodu BOOKS
Piegāde 17-23 darba dienu laikā
30 dienu atgriešanas politika
How can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical le ... Pilns apraksts
Jums varētu patikt arī
TOP
If Anyone Builds It, Everyone Dies: Why Superhuman AI Would Kill Us All
Eliezer Yudkowsky, Nate Soares
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Gödel, Escher, Bach: An Eternal Golden Braid
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
AI Engineering: Building Applications with Foundation Models
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
The Rust Programming Language
Steve Klabnik, Carol Nichols, Chris Krycho
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
The Art of Game Design: A Book of Lenses
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
How To Think About AI: A Guide For The Perplexed
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Empire of AI: Dreams and Nightmares in Sam Altman's OpenAI
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
The Pragmatic Programmer: journey to mastery, 20th Anniversary Edition, 2/e: your journey to mastery, 20th Anniversary Edition
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
HBR Guide to Generative AI for Managers
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Hackers. 25th Anniversary Edition: Heroes of the Computer Revolution
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
The Web Application Hacker's Handbook: Discovering and Exploiting Security Flaws
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
How Linux Works: What Every Superuser Should Know
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Artificial Intelligence: A Modern Approach, Global Edition
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Python Crash Course: A Hands-On, Project-Based Introduction to Programming
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Fundamentals of Software Architecture: A Modern Engineering Approach
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Speak Data: Artists, Scientists, Thinkers, and Dreamers on How We Live Our Lives in Numbers
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Linux Basics for Hackers, 2nd Edition: Getting Started with Networking, Scripting, and Security in Kali
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
C Programming Language
Brian W. Kernighan, Brian Kernighan, Dennis Ritchie
-30% ar kodu BOOKS
Piegādātāja noliktavā
TOP
Proofs from THE BOOK
Martin Aigner, Günter M. Ziegler
-30% ar kodu BOOKS
Piegādātāja noliktavā
Aprašymas
How can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory answers these questions by deriving non-asymptotic bounds on the generalization error of a model or, in other words, by upper bounding the true error of the learned model based just on quantities computed on the available data. However, for a long time, Statistical learning theory has been considered only an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this book is to give an intelligible overview of the problems of model selection and error estimation, by focusing on the ideas behind the different statistical learning theory approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. The book starts by presenting the seminal works of the 80¿s and includes the most recent results. It discusses open problems and outlines future directions for research.
Vairāk informācijas
| Autors | Luca Oneto |
|---|---|
| Izdevējs | Springer Nature Switzerland |
| Series | Modeling and Optimization in Science and Technologies |
| Izlaides gads | 2019 |
| Vāka tips | Cietais vāks |
| EAN | 9783030243586 |