Eecient Learning of Linear Perceptrons
نویسندگان
چکیده
We introduce an eecient agnostic learning algorithm for the class of half-spaces in < n. We make no assumptions whatsoever on the example-generating distribution. Our performance guarantee is that, given any > 0, our algorithm runs in time polynomial in the sample size and dimension, and outputs a hypothesis half-space that classiies correctly at least the number of points classiied correctly with margin by any other half-space. While our algorithm's running time is not polynomial in 1==, we prove that unless P=NP no such`fully polynomial' approximation scheme exists.
منابع مشابه
Ensemble learning of linear perceptrons; Online learning theory
Abstract Within the framework of on-line learning, we study the generalization error of an ensemble learning machine learning from a linear teacher perceptron. The generalization error achieved by an ensemble of linear perceptrons having homogeneous or inhomogeneous initial weight vectors is precisely calculated at the thermodynamic limit of a large number of input elements and shows rich behav...
متن کاملLocal linear perceptrons for classification
A structure composed of local linear perceptrons for approximating global class discriminants is investigated. Such local linear models may be combined in a cooperative or competitive way. In the cooperative model, a weighted sum of the outputs of the local perceptrons is computed where the weight is a function of the distance between the input and the position of the local perceptron. In the c...
متن کاملOn Boolean Combinations of Definitive Classifiers
We consider the sample complexity of concept learning when we classify by using a fixed Boolean function of the outputs of a number of different classifiers. Here, we take into account the ‘margins’ of each of the constituent classifiers. A special case is that in which the constituent classifiers are linear threshold functions (or perceptrons) and the fixed Boolean function is the majority fun...
متن کاملNonlinear Classification using Ensemble of Linear Perceptrons
In this study we introduce a neural network ensemble composed of several linear perceptrons, to be used as a classifier that can rapidly be trained and effectively deals with nonlinear problems. Although each member of the ensemble can only deal with linear classification problems, through a competitive training mechanism, the ensemble is able to automatically allocate a part of the learning sp...
متن کاملLETTER Communicated by Sun - Ichi AmariOn \ Natural " Learning and Pruning in Multilayered PerceptronsTom
Several studies have shown that natural gradient descent for on-line learning is much more eecient than standard gradient descent. In this paper, we derive natural gradients in a slightly diierent manner and discuss implications for batch-mode learning and pruning, linking them to existing algorithms such as Levenberg-Marquardt optimization and optimal brain surgeon. The Fisher matrix plays an ...
متن کامل