The paper makes a brief introduction into multiple classifier systems and describes a particular algorithm which improves classification accuracy by making a recommendation of an algorithm to an object. This recommendation is done under a hypothesis that a classifier is likely to predict the label of the object correctly if it has correctly classified its neighbors. The process of assigning a classifier to each object involves here the apparatus of Formal Concept Analysis. We explain the principle of the algorithm on a toy example and describe experiments with real-world datasets.
The problem of realization of Boolean functions by initial Boolean automata with constant states and n inputs is considered. Initial Boolean automaton with constant states and n inputs is an initial automaton with output such that in all states output functions are n-ary constant Boolean functions 0 or 1. All sets of the maximum cardinality of n-ary Boolean functions realized by an initial Boolean automaton with two or three constant states provided to the possibility of an arbitrary order of input values is obtained.
In this paper we consider the Shape Boltzmann Machine(SBM) and its multi-label version MSBM. We present an algorithm for training MSBM using only binary masks of objects and the seeds which approximately correspond to the locations of objects parts.
A hyperautomatа is a finite automatа whose states are the sets of states of some finite automata. A hyperautomatа is called a group hyperautomatа if the semigroup of the automatа on which it is based is a finite group. In this paper, we study the question of the maximum number of regular languages that can be recognized by group hyperautomata.
Variational autoencoder (VAE) is a probabilistic unsupervised method that uses deep learning. We propose a robust approach to the training of VAE using a modified likelihood function. We propose and analyze two variational lower bound objectives. The effectiveness of the method is experimentally shown by artificially introducing noise objects.
One of the main tasks of the theory of collective choice is formulated in the language of functional Galois correspondences. A convenient characterization of symmetric classes of decision rules without the Arrow property is proposed.