Matrix Pseudoinversion for Image Neural Processing
Recently some novel strategies have been proposed for training of Single Hidden Layer Feedforward Networks, that set randomly the weights from input to hidden layer, while weights from hidden to output layer are analytically determined by Moore-Penrose generalised inverse. Such non-iterative strategies are appealing since they allow fast learning, but some care may be required to achieve good results, mainly concerning the procedure used for matrix pseudoinversion. This paper proposes a novel approach based on original determination of the initialization interval for input weights, a careful choice of hidden layer activation functions and on critical use of generalised inverse to determine output weights. We show that this key step suffers from numerical problems related to matrix invertibility, and we propose a heuristic procedure for bringing more robustness to the method. We report results on a difficult astronomical image analysis problem of chromaticity diagnosis to illustrate the various points under study.
KeywordsPseudoinverse matrix Weights initialization Supervised learning
Unable to display preview. Download preview PDF.
- 4.Nguyen, T.D., Pham, H.T.B., Dang, V.H.: An efficient Pseudo Inverse matrix-based solution for secure auditing. In: IEEE International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future (2010)Google Scholar
- 6.Ajorloo, H., Manzuri-Shalmani, M.T., Lakdashti, A.: Restoration of Damaged Slices in Images Using Matrix Pseudo Inversion. In: 22th International Symposium on Computer and Information Sciences, Ankara, pp. 98–104 (2007)Google Scholar
- 7.Bini, D., Capovani, M., Menchi, O.: Metodi numerici per l’algebra lineare. Ed. Zanichelli, Bologna (1988)Google Scholar
- 8.Bishop, C. M.: Pattern Recognition and Machine Learning. Ed. Springer, Berlin (2006)Google Scholar
- 12.Le Gall, J.Y., Saisse, M.: Chromatic Aberration of an All-Reflective Telescope. In: Instrumentation in Astronomy V, London. SPIE, vol. 445, pp. 497–504 (1983)Google Scholar
- 13.Perryman, M.A.C., et al.: GAIA - Composition, formation and evolution of the galaxy. Concept and technology study, Rep. and Exec. Summary. In: European Space Agency, ESA-SCI, Munich, Germany, vol. 4 (2000)Google Scholar
- 15.Cancelliere, R., Gai, M.: Efficient computation and Neural Processing of Astrometric Images. Computing and Informatics 28, 711–727 (2009)Google Scholar
- 16.Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: 13th International Conference on Artificial Intelligence and Statistics, AISTATS 2010, Chia, Italy (2010)Google Scholar