The model of the hybrid neural network is considered. This model consists of model ART-2 for clusterization 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.
Architecture of the toolkit ESWin and hybrid expert systems, supported by one, are described in this report. The knowledge representation by rules, frames and linguistic variables is used in this architecture. The possibility of keeping and extraction of data from external databases, execute of external programs are provided. This architecture supports of… (More)
The architecture of control system for mobile robots is proposed in this paper. This architecture is based on hybrid approach using neural networks for classification of images and organization of associative memory as well as semantic networks for natural language processing and organization of memory and achievment of goals. In last decade investigators… (More)
In this paper architecture of hybrid control system of robot based on context and learning by natural language is suggested. 1. Introduction One of challenges in development of intelligent robots and other intelligent agents is human-robot interface. Two kinds of such known interfaces are oriented on programming and learning respectively. Programming is… (More)
s. The model of associative memory is proposed in this paper based on concept of association between images and associative search. This model may be used for connect concept of inference with associative processing in neural networks. A main problem of knowledge processing in intelligent system, is the problem of search of relevant knowledge or, in other… (More)
In this chapter hybrid approach to development of intelligent systems is applied to ubiquitous computing systems, in particular, to smart environment. Different classifications of Hybrid Intelligent Systems (HIS) are looking and two examples of hybrid approach for smart environment are suggested: framework based on expert system and neural network for… (More)
A three-dimensional dynamic reconstruction algorithm of the left ventricle of patient’s heart from ultrasonic echocardiography data is developed. The presented algorithm takes into account the longitudinal and transverse velocities of ventricle walls to determine the motion vectors of the ventricular walls. Two longitudinal ultrasonic sections (four-chamber… (More)
Goal of course: provide of study by students features of different neural network models and its application for solving of different tasks, skill in programming of neural networks for solving of concrete task Contents of lectures: Introduction. Different approaches to modeling and using of neural networks Features of construction and working of brain… (More)