Machine Learning from Weak Supervision: An Empirical Risk Minimization Approach by Sugiyama, Masashi

Machine Learning from Weak Supervision: An Empirical Risk Minimization Approach

Fundamental theory and practical algorithms of weakly supervised classification, emphasizing an approach based on empirical risk minimization....
BD$163.21 BMD
BD$163.21 BMD
SKU: 9780262047074
Product Type: Books
Please hurry! Only 0 left in stock
Author: Masashi Sugiyama
Format: Hardcover
Language: English
Subtotal: BD$163.21
10 customers are viewing this product
Machine Learning from Weak Supervision: An Empirical Risk Minimization Approach by Sugiyama, Masashi

Machine Learning from Weak Supervision: An Empirical Risk Minimization Approach

BD$163.21

Machine Learning from Weak Supervision: An Empirical Risk Minimization Approach

BD$163.21
Author: Masashi Sugiyama
Format: Hardcover
Language: English
Fundamental theory and practical algorithms of weakly supervised classification, emphasizing an approach based on empirical risk minimization.

Standard machine learning techniques require large amounts of labeled data to work well. When we apply machine learning to problems in the physical world, however, it is extremely difficult to collect such quantities of labeled data. In this book Masashi Sugiyama, Han Bao, Takashi Ishida, Nan Lu, Tomoya Sakai and Gang Niu present theory and algorithms for weakly supervised learning, a paradigm of machine learning from weakly labeled data. Emphasizing an approach based on empirical risk minimization and drawing on state-of-the-art research in weakly supervised learning, the book provides both the fundamentals of the field and the advanced mathematical theories underlying them. It can be used as a reference for practitioners and researchers and in the classroom.

The book first mathematically formulates classification problems, defines common notations, and reviews various algorithms for supervised binary and multiclass classification. It then explores problems of binary weakly supervised classification, including positive-unlabeled (PU) classification, positive-negative-unlabeled (PNU) classification, and unlabeled-unlabeled (UU) classification. It then turns to multiclass classification, discussing complementary-label (CL) classification and partial-label (PL) classification. Finally, the book addresses more advanced issues, including a family of correction methods to improve the generalization performance of weakly supervised learning and the problem of class-prior estimation.

Author: Masashi Sugiyama, Han Bao, Takashi Ishida
Publisher: MIT Press
Published: 08/23/2022
Pages: 320
Binding Type: Hardcover
Weight: 1.65lbs
Size: 9.10h x 7.00w x 0.70d
ISBN: 9780262047074

Returns Policy

You may return most new, unopened items within 30 days of delivery for a full refund. We'll also pay the return shipping costs if the return is a result of our error (you received an incorrect or defective item, etc.).

You should expect to receive your refund within four weeks of giving your package to the return shipper, however, in many cases you will receive a refund more quickly. This time period includes the transit time for us to receive your return from the shipper (5 to 10 business days), the time it takes us to process your return once we receive it (3 to 5 business days), and the time it takes your bank to process our refund request (5 to 10 business days).

If you need to return an item, simply login to your account, view the order using the "Complete Orders" link under the My Account menu and click the Return Item(s) button. We'll notify you via e-mail of your refund once we've received and processed the returned item.

Shipping

We can ship to virtually any address in the world. Note that there are restrictions on some products, and some products cannot be shipped to international destinations.

When you place an order, we will estimate shipping and delivery dates for you based on the availability of your items and the shipping options you choose. Depending on the shipping provider you choose, shipping date estimates may appear on the shipping quotes page.

Please also note that the shipping rates for many items we sell are weight-based. The weight of any such item can be found on its detail page. To reflect the policies of the shipping companies we use, all weights will be rounded up to the next full pound.

Related Products

Recently Viewed Products