Skip to content

We apologise for issues customers may be experiencing with accessing the Cambridge website. We are working hard to restore stability to the platform.

Cart
Register Sign in Wishlist

Algebraic Geometry and Statistical Learning Theory

$93.00

Part of Cambridge Monographs on Applied and Computational Mathematics

  • Date Published: August 2009
  • availability: Available
  • format: Hardback
  • isbn: 9780521864671

$ 93.00
Hardback

Add to cart Add to wishlist

Other available formats:
eBook


Looking for an evaluation copy?

This title is not currently available for evaluation. However, if you are interested in the title for your course we can consider offering an evaluation copy. To register your interest please contact asiamktg@cambridge.org providing details of the course you are teaching.

Description
Product filter button
Description
Contents
Resources
Courses
About the Authors
  • Sure to be influential, this book lays the foundations for the use of algebraic geometry in statistical learning theory. Many widely used statistical models and learning machines applied to information science have a parameter space that is singular: mixture models, neural networks, HMMs, Bayesian networks, and stochastic context-free grammars are major examples. Algebraic geometry and singularity theory provide the necessary tools for studying such non-smooth models. Four main formulas are established: 1. the log likelihood function can be given a common standard form using resolution of singularities, even applied to more complex models; 2. the asymptotic behaviour of the marginal likelihood or 'the evidence' is derived based on zeta function theory; 3. new methods are derived to estimate the generalization errors in Bayes and Gibbs estimations from training errors; 4. the generalization errors of maximum likelihood and a posteriori methods are clarified by empirical process theory on algebraic varieties.

    • ● Presents a new statistical theory for singular learning machines ● Mathematical concepts explained for non-specialists ● Intended for any student interested in machine learning, pattern recognition, artificial intelligence or bioinformatics
    Read more

    Customer reviews

    Not yet reviewed

    Be the first to review

    Review was not posted due to profanity

    ×

    , create a review

    (If you're not , sign out)

    Please enter the right captcha value
    Please enter a star rating.
    Your review must be a minimum of 12 words.

    How do you rate this item?

    ×

    Product details

    • Date Published: August 2009
    • format: Hardback
    • isbn: 9780521864671
    • length: 300 pages
    • dimensions: 229 x 152 x 20 mm
    • weight: 0.54kg
    • contains: 13 b/w illus.
    • availability: Available
  • Table of Contents

    Preface
    1. Introduction
    2. Singularity theory
    3. Algebraic geometry
    4. Zeta functions and singular integral
    5. Empirical processes
    6. Singular learning theory
    7. Singular learning machines
    8. Singular information science
    Bibliography
    Index.

  • Resources for

    Algebraic Geometry and Statistical Learning Theory

    Sumio Watanabe

    General Resources

    Welcome to the resources site

    Here you will find free-of-charge online materials to accompany this book. The range of materials we provide across our academic and higher education titles are an integral part of the book package whether you are a student, instructor, researcher or professional.

    Find resources associated with this title

    Type Name Unlocked * Format Size

    Showing of

    Back to top

    *This title has one or more locked files and access is given only to lecturers adopting the textbook for their class. We need to enforce this strictly so that solutions are not made available to students. To gain access to locked resources you either need first to sign in or register for an account.


    These resources are provided free of charge by Cambridge University Press with permission of the author of the corresponding work, but are subject to copyright. You are permitted to view, print and download these resources for your own personal use only, provided any copyright lines on the resources are not removed or altered in any way. Any other use, including but not limited to distribution of the resources in modified form, or via electronic or other media, is strictly prohibited unless you have permission from the author of the corresponding work and provided you give appropriate acknowledgement of the source.

    If you are having problems accessing these resources please email lecturers@cambridge.org

  • Author

    Sumio Watanabe, Tokyo Institute of Technology
    Sumio Watanabe is a Professor in the Precision and Intelligence Laboratory at the Tokyo Institute of Technology.

Sign In

Please sign in to access your account

Cancel

Not already registered? Create an account now. ×

Sorry, this resource is locked

Please register or sign in to request access. If you are having problems accessing these resources please email lecturers@cambridge.org

Register Sign in
Please note that this file is password protected. You will be asked to input your password on the next screen.

» Proceed

You are now leaving the Cambridge University Press website. Your eBook purchase and download will be completed by our partner www.ebooks.com. Please see the permission section of the www.ebooks.com catalogue page for details of the print & copy limits on our eBooks.

Continue ×

Continue ×

Continue ×

Find content that relates to you

This site uses cookies to improve your experience. Read more Close

Are you sure you want to delete your account?

This cannot be undone.

Cancel

Thank you for your feedback which will help us improve our service.

If you requested a response, we will make sure to get back to you shortly.

×
Please fill in the required fields in your feedback submission.
×