Scholarly record
THE STUDY ALGORITHMS FOR THE IDENTIFICATION OF THE FIGURES
Abstract
The Artificial Intelligence is a measure of the ability to achieve purposes in a complex and dynamic.The recognition of the figures using artificial intelligence has been and is still one of the great problems of the modern era. The attempt of identification of the figures in various forms, the contours and shades has developed an impressive number of algorithms. Up until now it has not been discovered the optimum method and algorithm with an efficiency of 100 % in recognition of the figures.The front work proposes the implementation of a system for the recognition of figures, both by experiments, and the appropriateness of theoretical and case study on the behavior and efficiency of a network node with variable number of neurons.
Publication Impact Profile
Publication details
References10
Neagoe Victor S.T., The recognition of forms and neural networks. The fundamental algorithms, The publishing house Matrix Rom, Bucharest, 1998
Neagoe Victor S.T., The theory of recognition forms, The Romanian Academy's publishing house, Bucharest, 1992
Cârţină Gheorghe S.T., The artificial neuronal networks and systems expert in energy efficiency, Gheorghe Asachi publishing house, Iași, 1994
Prasad, K., et al., Character recognition using matlab’s neural network toolbox, Int. J. u-e-Serv. Sci. Technol. 6(1), pp 13–20, 2013
Tudor N. L., Intelligent system for time series prediction in stock exchange markets, Proceedings of the 17th International Conference on Business Information Systems (BIS), Larnaca, Cyprus, 22-23 May, LNBIP 176, pp. 122-133, Springer International Publishing Switzerland, W. Abramowicz and A. Kokkinaki (Eds.), 2014 (Conference Australian Research Council) http://bis.kie.ue.poznan.pl/17th_bis/
http://www.math.hkbu.edu.hk/~cstong/sci3710/filter_tutor.html - 20.02.2011
http://sebastianraschka.com/Articles/2015_singlelayer_neurons.html
Machine Learning with Tensorflow – https://www.manning.com/books/machine-learning-with-tensorflow
Glorot, X., Bordes, A., and Bengio, Y., Deep sparse rectifier neural networks. In JMLR W&CP, Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2011), 2011
Sermanet, P., Chintala, S., and LeCun, Y., Convolutional neural networks applied to house numbers digit classification, In International Conference on Pattern Recognition (ICPR 2012), 2012
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.
