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 presented article is about a research using artificial neural network (ANN) methods for compound (technical and fundamental) analysis and prognosis of Lithuania's National Stock Exchange (LNSE) indices LITIN, LITIN-A and LITIN-VVP. We employed initial pre-processing (analysis for entropy and correlation) for filtering out model input variables (LNSE indices, macroeconomic indicators, Stock Exchange indices of other countries such as the USA – Dow Jones and S&P, EU – Eurex, Russia – RTS). Investigations for the best approximation and forecasting capabilities were performed using different backpropagation ANN learning algorithms, configurations, iteration numbers, data form-factors, etc. A wide spectrum of different results has shown a high sensitivity to ANN parameters. ANN autoregressive, autoregressive causative and causative trend model performances were compared in the approximation and forecasting by a linear discriminant analysis.

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.