Informatica

Text categorization – the assignment of natural language documents to one or more predefined categories based on their semantic content – is an important component in many information organization and management tasks. Performance of neural networks learning is known to be sensitive to the initial weights and architecture. This paper discusses the use multilayer neural network initialization with decision tree classifier for improving text categorization accuracy. Decision tree from root node until a final leave is used for initialization of each single unit. Growing decision trees with increasingly larger amounts of training data will result in larger decision tree sizes. As a result, the neural networks constructed from these decision trees are often larger and more complex than necessary. Appropriate choice of certainty factor is able to produce trees that are essentially constant in size in the face of increasingly larger training sets. Experimental results support the conclusion that error based pruning can be used to produce appropriately sized trees, which are directly mapped to optimal neural network architecture with good accuracy. The experimental evaluation demonstrates this approach provides better classification accuracy with Reuters‐21578 corpus, one of the standard benchmarks for text categorization tasks. We present results comparing the accuracy of this approach with multilayer neural network initialized with traditional random method and decision tree classifiers.

The analysis of the method for multiple criteria optimization problems applying a computer network has been presented in the paper. The essence of the proposed method is the distribution of the concrete optimization problem into the network rather than the parallelization of some optimization method. The aim of the authors is to design and investigate the interactive strategies to solve complex multiple criteria problems by applying a computer network. The optimized objective function is the weight sum of the criteria. The multiple criteria problem is iterated by selecting interactively different weight coefficients of the criteria. Therefore, the process is organized by designating the computers as the master (that coordinates the process of other computers) and the slaves (that execute different tasks). In the beginning of the process the researcher allocates a certain number of optimization problems to the network. The objective function optimization problems differ only in weight coefficients of the criteria. As soon as the task of a slave has been executed, the result is sent to the master. Every computer of the network behaves in analogous way. Whenever the researcher receives an immediate result from one of the computers, he gives a decision taking into consideration the latter and all the previous results, i.e., he selects new weight coefficients for the criteria and assigns a new task to the network. Likewise the multiple criteria problem is solved until the result is acceptable for the researcher. The application of the proposed method is illustrated on the basis of the problem for the selection of the optimal nutritive value. Message Passing Interface (MPI) software has been used. The trials have been carried out with the network of computers under the operation system Windows NT.

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 recognition 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 artificial 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.

In the present paper, the method of structure analysis for multivariate functions was applied to rational approximation in classification problems. Then the pattern recognition and generalisation ability was investigated experimentally in numerical recognition. A comparison with Hopfield Net was carried out. The overall results of using of new approach may be treated as a success.

Neural networks are often characterized as highly nonlinear systems of fairly large amount of parameters (in order of 10³ – 10⁴). This fact makes the optimization of parameters to be a nontrivial problem. But the astonishing moment is that the local optimization technique is widely used and yields reliable convergence in many cases. Obviously, the optimization of neural networks is high-dimensional, multi-extremal problem, so, as usual, the global optimization methods would be applied in this case. On the basis of Perceptron-like unit (which is the building block for the most architectures of neural networks) we analyze why the local optimization technique is so successful in the field of neural networks. The result is that a linear approximation of the neural network can be sufficient to evaluate the start point for the local optimization procedure in the nonlinear regime. This result can help in developing faster and more robust algorithms for the optimization of neural network parameters.