Artificial Neural Networks Implementation in Digital Signal Processing Courses

The paper is dedicated to the implementation of the artificial neural networks in the laboratories on digital signal processing. The method described is based on artificial neural network implementation. Different architectures and types of artificial neural networks are compared. The training and testing sequences generation problem is discussed. The aim of the irregular mesh coverage of the two-dimensional signal (frame) is to decrease computational cost for the further motion detection between frames. The benefits of the artificial neural network usage are made clear and understandable for the students. Generalized results obtained may be used for pattern recognition, data compression, multidimensional look-up table interpolation. The educational impact of the method proposed is also discussed.