✦ LIBER ✦

On the generalization ability of on-line learning algorithms

✍ Scribed by Cesa-Bianchi, N.; Conconi, A.; Gentile, C.

Book ID: 114638411
Publisher: IEEE
Year: 2004
Tongue: English
Weight: 213 KB
Volume: 50
Category: Article
ISSN: 0018-9448
DOI: 10.1109/tit.2004.833339

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

On the Boosting Ability of Top–Down Deci

On the Boosting Ability of Top–Down Decision Tree Learning Algorithms

✍ Michael Kearns; Yishay Mansour 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 513 KB

We analyze the performance of top down algorithms for decision tree learning, such as those employed by the widely used C4.5 and CART software packages. Our main result is a proof that such algorithms are boosting algorithms. By this we mean that if the functions that label the internal nodes of the

Accurate estimates of the generalization

Accurate estimates of the generalization ability for symmetric set of predictors and randomized learning algorithms

✍ A. I. Frei 📂 Article 📅 2010 🏛 SP MAIK Nauka/Interperiodica 🌐 English ⚖ 296 KB

Adaptive and Self-Confident On-Line Lear

Adaptive and Self-Confident On-Line Learning Algorithms

✍ Peter Auer; Nicolò Cesa-Bianchi; Claudio Gentile 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 216 KB

We study on-line learning in the linear regression framework. Most of the performance bounds for on-line algorithms in this framework assume a constant learning rate. To achieve these bounds the learning rate must be optimized based on a posteriori information. This information depends on the whole

On the Generalization Ability of GRLVQ N

On the Generalization Ability of GRLVQ Networks

✍ Barbara Hammer; Marc Strickert; Thomas Villmann 📂 Article 📅 2005 🏛 Springer US 🌐 English ⚖ 268 KB

On the generalization of soft margin alg

On the generalization of soft margin algorithms

✍ Shawe-Taylor, J.; Cristianini, N. 📂 Article 📅 2002 🏛 IEEE 🌐 English ⚖ 515 KB

Line Generalization on the Sphere

✍ James E. Burt 📂 Article 📅 2010 🏛 John Wiley and Sons 🌐 English ⚖ 491 KB