We construct a modi ed perceptron algorithm that is deterministic, polynomial and also as fast as previous known algorithms. The algorithm runs in time O(mn log n log(1/ρ)), where m is the number of examples, n the number of dimensions and ρ is approximately the size of the margin. We also construct a non-deterministic modi ed perceptron algorithm running in time O(mn log n log(1/ρ)). 1 A Deter...

In ensemble teacher learning, ensemble teachers have only uncertain information about the true teacher, and this information is given by an ensemble consisting of an infinite number of ensemble teachers whose variety is sufficiently rich. In this learning, a student learns from an ensemble teacher that is iteratively selected randomly from a pool of many ensemble teachers. An interesting point ...

| An algorithm is proposed for training the single-layered per-ceptron. The algorithm follows successive steepest descent directions with respect to the perceptron cost function, taking care not to increase the number of misclassiied patterns. The problem of nding these directions is stated as a quadratic programming task, to which a fast and eeective solution is proposed. The resulting algorit...

Recurrent perceptron classifiers generalize the classical perceptron model. They take into account those correlations and dependences among input coordinates which arise from linear digital filtering. This paper provides tight bounds on sample complexity associated to the fitting of such models to experimental data.

The model of the hybrid neural network is considered. This model consists of model ART-2 for clustering and perceptron for preprocessing of images. The perceptron provides invariant recognition of objects. This model can be used in mobile robots for recognition of new objects or scenes in sight the robot during his movement.