Titlebook: Computational Learning Theory; 14th Annual Conferen David Helmbold,Bob Williamson Conference proceedings 2001 Springer-Verlag Berlin Heidel

cerebral

书目名称Computational Learning Theory影响因子(影响力)




书目名称Computational Learning Theory影响因子(影响力)学科排名




书目名称Computational Learning Theory网络公开度




书目名称Computational Learning Theory网络公开度学科排名




书目名称Computational Learning Theory被引频次




书目名称Computational Learning Theory被引频次学科排名




书目名称Computational Learning Theory年度引用




书目名称Computational Learning Theory年度引用学科排名




书目名称Computational Learning Theory读者反馈




书目名称Computational Learning Theory读者反馈学科排名

不能妥协

Radial Basis Function Neural Networks Have Superlinear VC Dimension,rons. As the main result we show that every reasonably sized standard network of radial basis function (RBF) neurons has VC dimension Ω([itW ] log .), where . is the number of parameters and . the number of nodes. This significantly improves the previously known linear bound. We also derive superlin

transient-pain

Tracking a Small Set of Experts by Mixing Past Posteriors,ves predictions from a large set of . experts. Its goal is to predict almost as well as the best sequence of such experts chosen off-line by partitioning the training sequence into .+1 sections and then choosing the best expert for each section. We build on methods developed by Herbster and Warmuth

MODE

Potential-Based Algorithms in Online Prediction and Game Theory,e and Warmuth’s Weighted Majority), for playing iterated games (including Freund and Schapire’s Hedge and MW, as well as the Λ-strategies of Hart and Mas-Colell), and for boosting (including AdaBoost) are special cases of a general decision strategy based on the notion of potential. By analyzing thi

Bricklayer

A Sequential Approximation Bound for Some Sample-Dependent Convex Optimization Problems with Applicons. This analysis is closely related to the regret bound framework in online learning. However we apply it to batch learning algorithms instead of online stochastic gradient decent methods. Applications of this analysis in some classification and regression problems will be illustrated.

前奏曲

前奏曲

Ultraconservative Online Algorithms for Multiclass Problems,pe vector per class. Given an input instance, a multiclass hypothesis computes a similarity-score between each prototype and the input instance and then sets the predicted label to be the index of the prototype achieving the highest similarity. To design and analyze the learning algorithms in this p

visual-cortex

indemnify

Adaptive Strategies and Regret Minimization in Arbitrarily Varying Markov Environments,is problem is captured by a two-person stochastic game model involving the reward maximizing agent and a second player, which is free to use an arbitrary (non-stationary and unpredictable) control strategy. While the minimax value of the associated zero-sum game provides a guaranteed performance lev

我就不公正

,Robust Learning — Rich and Poor,d classes T(.) where T is any general recursive operator, are learnable in the sense .. It was already shown before, see [14,19], that for . (learning in the limit) robust learning is rich in that there are classes being both not contained in any recursively enumerable class of recursive functions a