On practical constraints of approximation using neural networks on current digital computers

INES 2014 - IEEE 18th International Conference on Intelligent Engineering Systems, Proceedings

Volumn , Issue , 2014, Pages 257-262

  Puheim, Michal ^a   Nyulászi, Ladislav ^a   Madárasz, Ladislav ^a   Gašpar, Vladimír ^a  

^a TECHNICAL UNIVERSITY OF KO ICE   (Slovakia)

Author keywords

approximation constraints; artificial neural network; digital computers; multilayer perceptron; universal approximation theorem

Indexed keywords

APPROXIMATION THEORY; COMPUTER NETWORKS; DIGITAL ARITHMETIC; DIGITAL COMPUTERS; FEEDFORWARD NEURAL NETWORKS; MULTILAYERS; NEURAL NETWORKS;

APPROXIMATION CONSTRAINTS; DATA PRE TREATMENTS; DATA TYPE; FLOATING POINT OPERATIONS; FUNCTION APPROXIMATORS; MULTIPLE CONSTRAINT; ON CURRENTS; UNIVERSAL APPROXIMATION;

MULTILAYER NEURAL NETWORKS;

EID: 84908636617     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/INES.2014.6909379     Document Type: Conference Paper

References (20)

1. S. Nissen: "Fast Artificial Neural Network Library, "[Onli ne ]. 2013. Available: http://leenissen.dk/fann/wp/news/(Cited: 3. June 2014)
2. S. Nissen: "Neural Networks Made Simple, " [Online ]. 2013. Available: http://fann.sourceforge.net/fann-en.pdf (Cited: 3. June 2014)
3. M. Kárný , K. Warwick, V. K?rková: " The Psychological Limits of Neural Computation," In Dealing with Complexity, Perspectives in Neural Computing, Springer London, pp. 252-263. 1998. ISBN 978-3-540-76160-0
4. S. Haykin: "Neural Networks: A Comprehensive Foundation ", Volume 2, Prentice Hall. 1998. ISBN 0-13-273350-1.
5. P. Sin?á k, G. Andrejková: "Neuró nové siete-Inziniersky prístup," Dopredné neurónové siete, ?. 1. Kosice: Elfapress, 1996, ISBN 80-88786-38-X
6. B. Cs. Csáji: "Approximation with Artificial Neural Networks, " Master Thesis, Faculty of Sciences, E ötvös Loránd University, Hungary. 2001
7. W. S. McCulloch, W. H. Pitts: " A Logical Calculus of the Ideas Immanent in Nervous Activity," Bulletin of Mathematical Biophysics, Vol. 5, pp. 115-133. 1943.
8. A. N. Kolmogorov: " On the Representation of Continuous Functions of Several Variables by Superposition of Continuous Functions of one Variable and Addition," Doklady Akademii. Nauk USSR, 114, pp. 679-681. 1957.
9. G. Cybenko: "Approximation by Superpositions of a Sigmoidal Function, " Math. Control Signals Systems, 2, pp. 303-314. 1989.
10. K. Hornik, M. Stinchcombe, H. White:. " Multilayer Feedforward Networks are Universal Approximators," Neural Networks, 2(5), pp. 359-366. 1989.
11. K. Funahashi: " On the Approximate Realization of Continuous Mapping by Neural Networks," Neural Networks, Vol.2, pp. 183-192, 1989.
12. M.G. Augasta and T. Kathirvalavakumar: "Pruning algorithms of neural networks-A comparative study ", Central European Journal of Computer Science,Vol. 3, pp. 105-115. 2013. ISSN 1896-1533.
13. D. E. Rumelhart, G. E. Hinton, R. J. Williams: " Learning representations by back-propagating errors," Nature, Vol. 323, pp. 533-536. 1986.
14. X. Glorot, Y. Bengio: " Understanding the difficulty of training deep feedforward neural networks," Proc. of the 13th International Conference on Artificial Intelligence and Statistics, Chia Laguna Resort, Sardinia, Italy. 2010.
15. M. Gregor, P. Groumpos: " Tuning the position of a fuzzy cognitive map attractor using back propagation through time," 7th International Conference on Integrated Modeling and Analysis in Applied Control and Automation. Athens, Greece, 25-27 September 2013.
16. M. Puheim, L. Madará sz: " Normalization of Inputs and Outputs of Neural Network Based Robotic Arm Controller in Role of Inverse Kinematic Model." IEEE 12th International Symposium on Applied Machine Intelligence and Informatics. Her?any, Slovak Republic. 2014.
17. F. Piazza, A. Uncini, M. Zenobi: " Neural networks with digital LUT activation functions," Proc. of 1993 International Joint Conference on Neural Networks, vol.2, pp. 1401-1404. 25-29 Oct. 1993. DOI: 10.1109/IJCNN.1993.716806
18. N. Hahm B. Hong Il:i The Capability of Localized Neural Network Approximation Honam Mathematical Journal 35 Issue 4 729-738. 2013. 10.5831/HMJ.2013.35.4.729
19. Bao Jian, Chen Yu, Yu Jinshou: "Ne ural Networks with Limited Precision Weights and Its Application in Embedded Systems," International Workshop on Education Technology and Computer Science, pp. 86-91. 2010. DOI: 10.1109/ETCS.2010.448
20. D.H. W olpert, W.G. Macready: " No Free Lunch Theorems for Optimization" , IEEE Transactions on Evolutionary Computation 1, pp. 67-82. 1997. ISSN : 1089-778X