Šiame magistriniame darbe išanalizuota dirbtinių neuroninių tinklų teorija. Detaliai išnagrinėtas atgalinio klaidos sklidimo algoritmas. Pagal jį parašytos programos: C++ kalba ir Matlab sistemoje su siūlomais neuroninių tinklų konstravimo įrankiais. Lyginant programas atlikti tyrimai su irisų ir vyno atpažinimo duomenimis. Tyrimo metu ištirti ir paanalizuoti daugiasluoksniai neuroniniai tinklai su paslėptais vienu ir dviem sluoksniais. / This paper offers a profound research the theory of artificial neural network. It gives a deep analysis of error back propagation and provides error back propagation program written in C++ language and Matlab system with relevant neural network construction tools. To compare both programs I carried out research of wines recognition data and irises data. Analyzed feedforward neural network with hidden one and two layers.

Various techniques of optimizing the multiple class cross-entropy error function to train single hidden layer neural network classifiers with softmax output transfer functions are investigated on a real-world multispectral pixel-by-pixel classification problem that is of fundamental importance in remote sensing. These techniques include epoch-based and batch versions of backpropagation of gradient descent, PR-conjugate gradient and BFGS quasi-Newton errors. The method of choice depends upon the nature of the learning task and whether one wants to optimize learning for speed or generalization performance. It was found that, comparatively considered, gradient descent error backpropagation provided the best and most stable out-of-sample performance results across batch and epoch-based modes of operation. If the goal is to maximize learning speed and a sacrifice in generalisation is acceptable, then PR-conjugate gradient error backpropagation tends to be superior. If the training set is very large, stochastic epoch-based versions of local optimizers should be chosen utilizing a larger rather than a smaller epoch size to avoid inacceptable instabilities in the generalization results. (authors' abstract) / Series: Discussion Papers of the Institute for Economic Geography and GIScience