Weight assignment algorithms for designing fully connected neural network

Автор: Aarti M. Karande, D. R. Kalbande

Журнал: International Journal of Intelligent Systems and Applications @ijisa

Статья в выпуске: 6 vol.10, 2018 года.

Бесплатный доступ

Soft computing is used to solve the problems where input data is incomplete or imprecise. This paper demonstrate designing fully connected neural network system using four different weight calculation algorithms. Input data for weight calculation is constructed in the matrix format based on the pairwise comparison of input constraints. This comparison is performed using saaty’s method. This input matrix helps to build judgment between several individuals, forming a single judgment. Algorithm considered here are Geometric average mean, Linear algebra calculation, Successive matrix squaring method, and analytical hierarchical processing method. Based on the quality parameter of performance, it is observed that analytical hierarchical processing is the most promising mathematical method for finding appropriate weight. Analytical hierarchical processing works on structuration of the problem into sub problems, Hence it the most prominent method for weight calculation in fully connected NN.

Еще

Soft Computing, Neural Network, Saaty’s Method, Analytical Hierarchical Processing, Exact Linear Algebra Calculation, Geometric Average Approximation, Successive Matrix Squaring

Короткий адрес: https://readera.ru/15016501

IDR: 15016501   |   DOI: 10.5815/ijisa.2018.06.08

Список литературы Weight assignment algorithms for designing fully connected neural network

  • Abraham and Baikunth Nath, (2000) “Hybrid Intelligent Systems: Review of a Decade of Research” Technical Report Series, 5/2000
  • A.Maithili Dr R. Vasantha Kumari Mr S. Rajamanickam (2012) Neural Network towards Business Forecasting IOSR Journal of Engineering, pp: 831-836ISSN:2250-3021
  • Angela Bower (July 2003) Soft Computing tessell A Support Services Plc Issue V1.R1.M0
  • Ajith Abraham, Johnson Thomas, Marcin Paprzycki, Brent Doeksen,(2005)"Real Stock Trading Using Soft Computing Models", vol.02,pp.162-167,doi:10.1109/ITCC
  • Anita Ahmad Kasim Retantyo Wardoyo and Agus Harjoko (2017) Batik Classification with Artificial Neural Network Based on Texture-Shape Feature of Main Ornament I.J. Intelligent Systems and Applications, 2017, 6, 55-65 DOI: 10.5815/ijisa.2017.06.06 Copyright © 2017 MECS I.J. Intelligent Systems and Applications, 2017, 6, 55-65
  • Basheer M. Al-Maqaleh a , Abduhakeem A. Al-Mansou Fuad N. Al-Badani “Forecasting using Artificial Neural Network and Statistics Models” (2016) I.J. Education and Management Engineering, DOI:10.5815/ijeme.2016.03.03
  • Dragan Z. Šaletic (2006) “On Further Development of Soft Computing, Some Trends in Computational Intelligence” SISY 4th Serbian-Hungarian Joint Symposium on Intelligent Systems
  • Erich L. Kaltofen, Arne Storjohann “The Complexity of Computational Problems in Exact Linear Algebra” Encyclopaedia of Applied and Computational Mathematics, Bjorn Enquist, Mathematics of Computer Science, Discrete Mathematics,JohanHastad,field, Springer
  • Ebru Ardil and Parvinder S. Sandhu (2010) “A soft computing approach for modelling of severity of faults in software systems” International Journal of Physical Sciences Vol.5 (2), pp.074-085,ISSN 1992-1950
  • Ezhilarasi G and Dhavachelvan P (2010) “Effective Web Service Discovery Model Using Neural Network Approach” International Journal of Computer Theory and Engineering, Vol. 2, No. 5
  • Geoff Coyle: Practical Strategy (2004) Open Access Material. AHP © Pearson Education Limited
  • Prof. Dr. Hanan A. R. Akkar Firas R. Mahdi (2017) “Adaptive Path Tracking Mobile Robot Controller Based on Neural Networks and Novel Grass Root Optimization Algorithm” I.J. Intelligent Systems and Applications, 2017, 5, 1-9 DOI: 10.5815/ijisa.2017.05.01 MECS I.J. Intelligent Systems and Applications, 2017, 5, 1-9
  • Lujuan Chen, E.V. Krishnamurthy, Iain Macleod (1994) Generalized matrix inversion and rank computation by successive matrix powering parallel Computing20-297-311
  • Linear algebra: numerical methods. Version: Aug 12, 2000
  • Kurhe A.B., Satonkar S.S., Khanale P.B. and Shinde Ashok (2011) “Soft Computing and its Applications BIOINFO Soft Computing” Volume 1, Issue 1, pp-05-07
  • Kate A. Smith, Jatinder N.D. Gupta (2000) “Neural networks in business: techniques and applications for the operations researcher Computers & Operations Research 27 1023}1044
  • M.L. Caliusco and G. Stegmayer (2010) “Semantic Web Technologies and Artificial Neural Networks for Intelligent Web Knowledge Source Discovery” Y. Badr et al. (eds.) Emergent Web Intelligence: Advanced Semantic Technologies, Advanced Information and Knowledge Processing, DOI 10.1007/978-1-84996-077-9_2, © Springer-Verlag London Limited
  • Marco Miladinovic, Sladjana, predrag (2011) “Modified SMS method for computing outer inverses of Toeplitz matrices applied Mathematics and computation”
  • Qing Zhou, Yuxiang Wu, Christine W. Chan, Paitoon Tontiwachwuthikul (2011)“GHGT-10 from neural network to neuro-fuzzy modeling: applications to the carbon dioxide capture process” Energy Procedia 4 2066–2073
  • Roy Sterritt, David W. Bustard, (May 2002) “Fusing Hard and Soft Computing for Fault Management in Telecommunications Systems” IEEE Transactions On Systems, Man, And Cybernetics—Part C: Applications And Reviews, Vol. 32, No. 2
  • Robert Fuller Eotvos Lor (2001) Neuro-Fuzzy Methods for Modelling & Fault Diagnosis Lisbon Budapest Vacation School
  • S Xiaoji Liu, and Yonghui Qin (2012) “Successive Matrix Squaring Algorithm for Computing the Generalised Inverse A2” T Journal of Applied Mathematics, Article ID 262034, doi:10.1155/2012/262034
  • S Agatonovic-Kustrin, R Beresford (June 2000) “Basic concepts of artificial neural network (ANN) modelling and its application in pharmaceutical research” Journal of Pharmaceutical and Biomedical Analysis Vol 22, Issue5, https://doi.org/10.1016 /S0731-7085(99)00272-1
  • Mohd Shareduwan M. Kasihmuddin Mohd Asyraf Mansor Saratha Sathasivam (2016) “Bezier Curves Satisfiability Model in Enhanced Hopfield Network” I.J. Intelligent Systems and Applications, 2016, 12, 9-17 DOI: 10.5815/ijisa.2016.12.02
  • Tharwat O. S. Hanafy, H. Zaini, Kamel A. Shoush and Ayman A. Aly (2014) “Recent Trends in Soft Computing Techniques for Solving Real Time Engineering Problems” International Journal Of Control, Automation And Systems Vol.3 No.1 ISSN 2165-8277 ISSN 2165-8285
  • Thomas L. Saaty (2008) “Decision making with the analytic hierarchy process” Int. J. Services Sciences, Vol. 1, No. 1, 83 Copyright©2008 Inderscience Enterprises Ltd.
  • W. Suparta and K.M. Alhasa (2016) “Adaptive Neuro-Fuzzy Interference System, Modeling of Tropospheric Delays Using ANFIS” Springer Briefs in Meteorology, DOI10.1007/978-3-319-28437-8_2
  • Yimi Weia, Hebing Wub, Junyin Wei (Dec 2000) “Successive matrix squaring algorithm for parallel computing the weighted generalized inverse” AMN Applied Mathematics and Computation Volume 116, Issue 3, Pages 289–296
  • Book Reference: Neural Networks for Data Mining W6-2 Business Intelligence: A Managerial Approach
  • Web:cdiadvisors.com/papers/CDIArithmeticVsGeometric.Pdf
  • Web:http://www.publishyourarticles.net/knowledge-hub/ statistics/merits-and-demerits-of-geometric-mean-gm/1089
  • Web:https://www.wisdomjobs.com/e-university /quantitative-techniques-for-management-tutorial-297/measures-of-central-tendency-1592.html
  • Web:http://andrew.gibiansky.com/blog/machine-learning /fully-connected-neural-networks/
Еще
Статья научная