Statistical learning theory was introduced in the late 1960’s. Until the 1990’s it was a purely theoretical analysis of the problem of function estimation from a given collection of data. In the middle of the 1990’s new types of learning algorithms (called support vector machines) based

sedimentary rocks, cements, or biological tissues. To get a better theoretical insight onto restricted diffusion in multi-scale geometries, we study the spin-echo signal attenuation due to diffusion in circular and spherical layers, {x∈Rd: L–l<|x|<L}, presenting two geometrical lengths, the radius L

A paradox for “k-means clustering” k-means objective φ of C = {ci, i ∈ [k]} on a dataset X: φX(C) = x∈X ‖x − C(x)‖2, where C(x) = arg min c∈C ‖x − c‖ Even though approximation algorithms exist, they are rarely used for applications. Instead, a few heuristics, most notably Lloyd’s algorithm, are preferred and often successful in practice. Lloyd’s algorithm (a.k.a. the “k-means ” algorithm) Input: dataset X, |X | = n); k; samples size m, m> k.

This paper presents new algorithms for the maximum flow problem, the Hitchcock transportation problem, and the general minimum-cost flow problem. Upper bounds on ... the numbers of steps in these algorithms are derived, and are shown to compale favorably with upper bounds on the numbers of steps

reviews the important results from these studies and also presents new ideas and alternative interpretations which further explain the success of the EnKF. In addition to providing the theoretical framework needed for using the EnKF, there is also a focus on the algorithmic formulation and optimal

, inadequate atten-tion given to questions of definition and to the development of theoretical models that seek to explain, not simply to describe, the processes that bring individuals to leave institutions of higher education. With regard to the former, inadequate attention given to definition has often led

with learning about other items. This suggests that the neocortex learns slowly to discover the structure in ensembles of experiences. The hippocampal system permits rapid learning of new items without disrupting this structure, and reinstatement of new memories interleaves them with others to integrate them

In an earlier paper, we introduced a new “boosting” algorithm called AdaBoost which, theoretically, can be used to significantly reduce the error of any learning algorithm that consistently generates classifiers whose performance is a little better than random guessing. We also introduced

in this field. The Duality Principle relating stochastic estimation and deterministic control problems plays an important role in the proof of theoretical results. In several examples, the estimation problem and its dual are discussed side-by-side. Properties of the variance equation are of great interest

that techniques used in the analysis of Vapnik’s support vector classifiers and of neural networks with small weights can be applied to voting methods to relate the margin distribution to the test error. We also show theoretically and experimentally that boosting is especially effective at increasing the margins