메뉴 건너뛰기




Volumn 34, Issue 3, 2011, Pages 293-303

A method to improve the performance of multilayer perceptron by utilizing various activation functions in the last hidden layer and the least squares method

Author keywords

Activation functions; Least squares method; Multilayer perceptron

Indexed keywords

ACTIVATION FUNCTIONS; HIDDEN LAYERS; LEARNING PROCESS; LEAST SQUARES METHODS; MULTILAYER PERCEPTRON; NEURON ACTIVATION FUNCTION; SINGLE-STEP; SQUARED ERRORS;

EID: 84855563455     PISSN: 13704621     EISSN: 1573773X     Source Type: Journal    
DOI: 10.1007/s11063-011-9199-4     Document Type: Article
Times cited : (12)

References (17)
  • 1
    • 70350087544 scopus 로고    scopus 로고
    • Modified recursive least squares algorithm to train the hybrid multilayered perceptron (HMLP) network
    • Al-Batah MS, Isa NAM, Zamli KZ, Azizli KA (2010) Modified recursive least squares algorithm to train the hybrid multilayered perceptron (HMLP) network. Appl Soft Comput 10:236-244
    • (2010) Appl Soft Comput , vol.10 , pp. 236-244
    • Al-Batah, M.S.1    Isa, N.A.M.2    Zamli, K.Z.3    Azizli, K.A.4
  • 2
    • 0026820187 scopus 로고
    • Fast learning process of multilayer neural networks using recursive least squares method
    • Azimi-Sadjadi MR, Liou RJ (1992) Fast learning process of multilayer neural networks using recursive least squares method. IEEE Trans Signal Process 40(2):446-450
    • (1992) IEEE Trans Signal Process , vol.40 , Issue.2 , pp. 446-450
    • Azimi-Sadjadi, M.R.1    Liou, R.J.2
  • 4
    • 10044236527 scopus 로고    scopus 로고
    • Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation
    • Tseng CS, Chen CS (2004) Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation. Int J Intell Syst 19(12):1257-1275
    • (2004) Int J Intell Syst , vol.19 , Issue.12 , pp. 1257-1275
    • Tseng, C.S.1    Chen, C.S.2
  • 6
    • 0042131595 scopus 로고    scopus 로고
    • On function recovery by neural networks based on orthogonal expansions
    • PII S0362546X9700223X
    • Rafajowicz E, Pawlak M (1997) On function recovery by neural networks based on orthogonal expansions. In: Proc. 2nd world congress of nonlinear analysis. Nonlinear analysis, theory and applications, vol 30, no 3. Pergamon Press, Oxford, pp 1343-1354 (Pubitemid 127423749)
    • (1997) Nonlinear Analysis, Theory, Methods and Applications , vol.30 , Issue.3 , pp. 1343-1354
    • Rafajlowicz, E.1    Pawlak, M.2
  • 7
    • 48249104835 scopus 로고    scopus 로고
    • Fast and robust way of learning the Fourier series neural networks on the basis of multidimensional discrete Fourier transform
    • Springer, New York
    • Halawa K (2008) Fast and robust way of learning the Fourier series neural networks on the basis of multidimensional discrete Fourier transform. In: Lecture notes in computer science. Lecture notes in artificial intelligence, vol 5097. Springer, New York, pp 62-70
    • (2008) Lecture Notes in Computer Science. Lecture Notes in Artificial Intelligence , vol.5097 , pp. 62-70
    • Halawa, K.1
  • 8
    • 0027599793 scopus 로고
    • Universal approximation bounds for superpositions of a sigmoidal function
    • Barron AR (1993) Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans Inform Theory 39(3):930-945
    • (1993) IEEE Trans Inform Theory , vol.39 , Issue.3 , pp. 930-945
    • Barron, A.R.1
  • 10
    • 0030176172 scopus 로고    scopus 로고
    • A feedforward neural network with function shape autotuning
    • DOI 10.1016/0893-6080(96)00006-8
    • Chen C, Chang W (1996) A feedforward neural network with function shape autotuning. Neural Netw 9(4):627-641 (Pubitemid 26232898)
    • (1996) Neural Networks , vol.9 , Issue.4 , pp. 627-641
    • Chen, C.-T.1    Chang, W.-D.2
  • 11
    • 0032643084 scopus 로고    scopus 로고
    • Multilayer feedforward networks with adaptive spline activation function
    • Guarnieri S, Piazza F (1999) Multilayer feedforward networks with adaptive spline activation function. IEEE Trans Neural Netw 10(3):672-683
    • (1999) IEEE Trans Neural Netw , vol.10 , Issue.3 , pp. 672-683
    • Guarnieri, S.1    Piazza, F.2
  • 12
    • 0024880831 scopus 로고
    • Multilayer feedforward networks are universal approximators
    • DOI 10.1016/0893-6080(89)90020-8
    • Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359-366 (Pubitemid 20609008)
    • (1989) Neural Networks , vol.2 , Issue.5 , pp. 359-366
    • Hornik Kurt1    Stinchcombe Maxwell2    White Halbert3
  • 14
    • 78649934709 scopus 로고    scopus 로고
    • University of California, School of Information and Computer Science, Irvine
    • Frank A, Asuncion A (2011) UCI machine learning repository. University of California, School of Information and Computer Science, Irvine. http://archive.ics.uci.edu/ml
    • (2011) UCI Machine Learning Repository
    • Frank, A.1    Asuncion, A.2
  • 15
    • 72049084727 scopus 로고    scopus 로고
    • Modeling wine preferences by data mining from physicochemical properties
    • Cortez P, Cerdeira A, Almeida F, Matos T, Reis J (2009) Modeling wine preferences by data mining from physicochemical properties. Decis Support syst 47(4):547-553
    • (2009) Decis Support Syst , vol.47 , Issue.4 , pp. 547-553
    • Cortez, P.1    Cerdeira, A.2    Almeida, F.3    Matos, T.4    Reis, J.5
  • 16
    • 0037120623 scopus 로고    scopus 로고
    • Adata-driven software tool for enabling cooperative information sharing among police departments
    • Redmond MA, Baveja A (2002) Adata-driven software tool for enabling cooperative information sharing among police departments. Eur J Oper Res 141:660-678
    • (2002) Eur J Oper Res , vol.141 , pp. 660-678
    • Redmond, M.A.1    Baveja, A.2
  • 17
    • 84938959096 scopus 로고
    • Computer Files, Bureau of the Census, Census of Population and Housing 1990. United States: Summary Tape File 1a and 3a U.S. Department of Justice, Federal Bureau of Investigation, Crime in the United States, U.S. Department of Justice, Bureau of Justice Statistics, Law EnforcementManagement and Administrative Statistics, U.S. Department Of Commerce, Bureau Of The Census Producer, Washington and Inter-university Consortium for Political and Social Research Ann Arbor
    • Computer Files: Department of Commerce, Bureau of the Census, Census of Population and Housing 1990. United States: Summary Tape File 1a and 3a, U.S. Department of Justice, Federal Bureau of Investigation (1995) Crime in the United States, U.S. Department of Justice, Bureau of Justice Statistics, Law EnforcementManagement and Administrative Statistics. U.S. Department Of Commerce, Bureau Of The Census Producer, Washington and Inter-university Consortium for Political and Social Research Ann Arbor
    • (1995) Department of Commerce


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.