AdaBoost is a well known, effective technique for increasing the accuracy of learning algorithms. However, it has the potential to overfit the training set because its objective i...
In this paper we present a simple framework for activity recognition based on a model of multi-layered finite state machines, built on top of a low level image processing module f...
Recently we have proposed an algorithm of constructing hierarchical neural network classifiers (HNNC), that is based on a modification of error back-propagation. This algorithm co...
S. A. Dolenko, Yu. V. Orlov, I. G. Persiantsev, Ju...
The developmental approach enables us to build adaptive robots, and furthermore, to understand the essence of intelligence from the constructivist viewpoint. In this paper, a new d...
Various problems in machine learning, databases, and statistics involve pairwise distances among a set of objects. It is often desirable for these distances to satisfy the propert...