Algis Garliauskas

Hexagonal Approach and Modeling for the Visual Cortex

In this paper, the hexagonal approach was proposed for modeling the functioning of cerebral cortex, especially, the processes of learning and recognition of visual information. This approach is based on the real neurophysiological data of the structure and functions of cerebral cortex. Distinctive characteristic of the proposed neural network is the hexagonal arrangement of excitatory connections between neurons that enable the spreading or cloning of information on the surface of neuronal layer. Cloning of information and modification of the weight of connections between neurons are used as the basic principles for learning and recognition processes. Computer simulation of the hexagonal neural network indicated a suitability and prospectiveness of proposed approach in the creation, together with other modern concepts, of artificial neural network which will realize the most complicated processes that take place in the brain of living beings, such as short-term and long-term memory, episodic and declarative memory, recall, recognition, categori- sation, thinking, and others. Described neural network was realized with computer program written on Delfi 3 language named the first order hexagon brainware (HBW-1).

The neural network environmental model and software

The principles of a neural network environmental model are proposed. The principles are universal and can use different neural network architectures. Such a model is self-organizing, it can operate in both regimes with and without a teacher. It codes information about objects, their features, the actions operating in an environment, analyzes concrete situations. There are functions for making an action plan, for action control. The goal of the model is given from an external site. The model has more tha.n sixteen active regimes. The neural network environmental model is fulfilled in software a.nd hardware tools.

Learning and Recognition of Visual Patterns by Human Subjects and Artificial Intelligence Systems

Comparative study of the recognition of nonsemantic geometrical figures by the human subjects and ART neural network was carried out. The results of computer simulation experiments with ART neural network showed well correspondence with the psychophysical data on the recog- nition of different complexity visual patterns: in both cases the patterns of medium complexity were recognized with the highest accuracy. On the contrary, the recognition of the patterns by their informative fragments demonstrated different recognition strategies employed by natural and ar- tificial neural systems. For biological systems, it is necessary the presence of not only distinctive features in visual patterns but the redundant features as well for successive recognition. ART neural network ignores redundant features and recognizes visual patterns with equal accuracy whether the whole pattern or only the informative fragment of any completeness is present.

Control distributed parameter systems with orthogonal neural network learning

Adaptive Control Distributed Parameter Systems (ACDPS) with adaptive learning algorithms based on orthogonal neural network methodology are presented in this paper. We discuss a modification of orthogonal least squares learning to find appropriate efficient algorithms for solution of ACDPS problems. A two times problem linked with the real time of plant control dynamic processes and the learning time for adjustment of parameters in adaptive control of unknown distributed systems is discussed. The simulation results demonstrate that the orthogonallearning algorithms on a neural network concept allow to find perfectly tracked output control distributed parameters in ACDPS and have rather a good perspective in the development of generalised ACDSP theory and practice in the future.

About stochastic discrete neuronetworks

A stoc:hastic discrete neuronetwork is defined. In the investigation of discrete nelUonetworks probability methods are a.pplied a weak convergence of probability measures. Limit theorems (the strong la.w of large number and normal law) are proved for the stream of signals, going out of neurOllB.