Skip to main content

2019 | OriginalPaper | Buchkapitel

4. Perceptrons

verfasst von : Ke-Lin Du, M. N. S. Swamy

Erschienen in: Neural Networks and Statistical Learning

Verlag: Springer London

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

This chapter introduces the simplest form of neural network—the perceptron. The perceptron has its historical position in the discipline of neural network and machine learning. One-neuron perceptron and single-layer perctron are described, together with various training methods.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Amin, M. F., & Murase, K. (2009). Single-layered complex-valued neural network for real-valued classification problems. Neurocomputing, 72, 945–955.CrossRef Amin, M. F., & Murase, K. (2009). Single-layered complex-valued neural network for real-valued classification problems. Neurocomputing, 72, 945–955.CrossRef
2.
Zurück zum Zitat Amit, D. J., Wong, K. Y. M., & Campbell, C. (1989). Perceptron learning with sign-constrained weights. Journal of Physics A: Mathematical and General, 22, 2039–2045.MathSciNetCrossRef Amit, D. J., Wong, K. Y. M., & Campbell, C. (1989). Perceptron learning with sign-constrained weights. Journal of Physics A: Mathematical and General, 22, 2039–2045.MathSciNetCrossRef
3.
Zurück zum Zitat Auer, P., Hebster, M., & Warmuth, M. K. (1996). Exponentially many local minima for single neurons. In D. S. Touretzky, M. C. Mozer, & M. E. Hasselmo (Eds.), Advances in neural information processing systems (Vol. 8, pp. 316–322). Cambridge, MA: MIT Press. Auer, P., Hebster, M., & Warmuth, M. K. (1996). Exponentially many local minima for single neurons. In D. S. Touretzky, M. C. Mozer, & M. E. Hasselmo (Eds.), Advances in neural information processing systems (Vol. 8, pp. 316–322). Cambridge, MA: MIT Press.
4.
Zurück zum Zitat Auer, P., Burgsteiner, H., & Maass, W. (2008). A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural Networks, 21, 786–795.MATHCrossRef Auer, P., Burgsteiner, H., & Maass, W. (2008). A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural Networks, 21, 786–795.MATHCrossRef
5.
Zurück zum Zitat Bolle, D., & Shim, G. M. (1995). Nonlinear Hebbian training of the perceptron. Network, 6, 619–633.MATHCrossRef Bolle, D., & Shim, G. M. (1995). Nonlinear Hebbian training of the perceptron. Network, 6, 619–633.MATHCrossRef
6.
Zurück zum Zitat Bouboulis, P., & Theodoridis, S. (2011). Extension of Wirtinger’s calculus to reproducing kernel Hilbert spaces and the complex kernel LMS. IEEE Transactions on Signal Processing, 59(3), 964–978.MathSciNetMATHCrossRef Bouboulis, P., & Theodoridis, S. (2011). Extension of Wirtinger’s calculus to reproducing kernel Hilbert spaces and the complex kernel LMS. IEEE Transactions on Signal Processing, 59(3), 964–978.MathSciNetMATHCrossRef
7.
Zurück zum Zitat Castillo, E., Fontenla-Romero, O., Alonso-Betanzos, A., & Guijarro-Berdinas, B. (2002). A global optimum approach for one-layer neural networks. Neural Computation, 14(6), 1429–1449.MATHCrossRef Castillo, E., Fontenla-Romero, O., Alonso-Betanzos, A., & Guijarro-Berdinas, B. (2002). A global optimum approach for one-layer neural networks. Neural Computation, 14(6), 1429–1449.MATHCrossRef
8.
Zurück zum Zitat Cavallanti, G., Cesa-Bianchi, N., & Gentile, C. (2007). Tracking the best hyperplane with a simple budget perceptron. Machine Learning, 69, 143–167.CrossRef Cavallanti, G., Cesa-Bianchi, N., & Gentile, C. (2007). Tracking the best hyperplane with a simple budget perceptron. Machine Learning, 69, 143–167.CrossRef
9.
Zurück zum Zitat Chen, J. L., & Chang, J. Y. (2000). Fuzzy perceptron neural networks for classifiers with numerical data and linguistic rules as inputs. IEEE Transactions on Fuzzy Systems, 8(6), 730–745.CrossRef Chen, J. L., & Chang, J. Y. (2000). Fuzzy perceptron neural networks for classifiers with numerical data and linguistic rules as inputs. IEEE Transactions on Fuzzy Systems, 8(6), 730–745.CrossRef
10.
Zurück zum Zitat Crammer, K., Dekel, O., Shalev-Shwartz, S., & Singer, Y. (2005). Online passive aggressive algorithms. Journal of Machine Learning Research, 7, 551–585.MathSciNetMATH Crammer, K., Dekel, O., Shalev-Shwartz, S., & Singer, Y. (2005). Online passive aggressive algorithms. Journal of Machine Learning Research, 7, 551–585.MathSciNetMATH
11.
Zurück zum Zitat Diene, O., & Bhaya, A. (2009). Perceptron training algorithms designed using discrete-time control Liapunov functions. Neurocomputing, 72, 3131–3137.CrossRef Diene, O., & Bhaya, A. (2009). Perceptron training algorithms designed using discrete-time control Liapunov functions. Neurocomputing, 72, 3131–3137.CrossRef
12.
Zurück zum Zitat Duch, W. (2005). Uncertainty of data, fuzzy membership functions, and multilayer perceptrons. IEEE Transactions on Neural Networks, 16(1), 10–23.CrossRef Duch, W. (2005). Uncertainty of data, fuzzy membership functions, and multilayer perceptrons. IEEE Transactions on Neural Networks, 16(1), 10–23.CrossRef
13.
Zurück zum Zitat Duda, R. O., & Hart, P. E. (1973). Pattern classification and scene analysis. New York: Wiley.MATH Duda, R. O., & Hart, P. E. (1973). Pattern classification and scene analysis. New York: Wiley.MATH
14.
Zurück zum Zitat Eitzinger, C., & Plach, H. (2003). A new approach to perceptron training. IEEE Transactions on Neural Networks, 14(1), 216–221.CrossRef Eitzinger, C., & Plach, H. (2003). A new approach to perceptron training. IEEE Transactions on Neural Networks, 14(1), 216–221.CrossRef
15.
Zurück zum Zitat Fernandez-Delgado, M., Ribeiro, J., Cernadas, E., & Ameneiro, S. B. (2011). Direct parallel perceptrons (DPPs): Fast analytical calculation of the parallel perceptrons weights with margin control for classification tasks. IEEE Transactions on Neural Networks, 22(11), 1837–1848.CrossRef Fernandez-Delgado, M., Ribeiro, J., Cernadas, E., & Ameneiro, S. B. (2011). Direct parallel perceptrons (DPPs): Fast analytical calculation of the parallel perceptrons weights with margin control for classification tasks. IEEE Transactions on Neural Networks, 22(11), 1837–1848.CrossRef
16.
Zurück zum Zitat Fontenla-Romero, O., Guijarro-Berdinas, B., Perez-Sanchez, B., & Alonso-Betanzos, A. (2010). A new convex objective function for the supervised learning of single-layer neural networks. Pattern Recognition, 43(5), 1984–1992.MATHCrossRef Fontenla-Romero, O., Guijarro-Berdinas, B., Perez-Sanchez, B., & Alonso-Betanzos, A. (2010). A new convex objective function for the supervised learning of single-layer neural networks. Pattern Recognition, 43(5), 1984–1992.MATHCrossRef
17.
Zurück zum Zitat Frean, M. (1992). A thermal perceptron learning rule. Neural Computation, 4(6), 946–957.CrossRef Frean, M. (1992). A thermal perceptron learning rule. Neural Computation, 4(6), 946–957.CrossRef
18.
Zurück zum Zitat Freund, Y., & Schapire, R. (1999). Large margin classification using the perceptron algorithm. Machine Learning, 37, 277–296.MATHCrossRef Freund, Y., & Schapire, R. (1999). Large margin classification using the perceptron algorithm. Machine Learning, 37, 277–296.MATHCrossRef
19.
Zurück zum Zitat Gallant, S. I. (1990). Perceptron-based learning algorithms. IEEE Transactions on Neural Networks, 1(2), 179–191.MathSciNetCrossRef Gallant, S. I. (1990). Perceptron-based learning algorithms. IEEE Transactions on Neural Networks, 1(2), 179–191.MathSciNetCrossRef
20.
Zurück zum Zitat Gentile, C. (2001). A new approximate maximal margin classification algorithm. Journal of Machine Learning Research, 2, 213–242.MathSciNetMATH Gentile, C. (2001). A new approximate maximal margin classification algorithm. Journal of Machine Learning Research, 2, 213–242.MathSciNetMATH
21.
Zurück zum Zitat Gori, M., & Maggini, M. (1996). Optimal convergence of on-line backpropagation. IEEE Transactions on Neural Networks, 7(1), 251–254.CrossRef Gori, M., & Maggini, M. (1996). Optimal convergence of on-line backpropagation. IEEE Transactions on Neural Networks, 7(1), 251–254.CrossRef
22.
Zurück zum Zitat Hassoun, M. H., & Song, J. (1992). Adaptive Ho-Kashyap rules for perceptron training. IEEE Transactions on Neural Networks, 3(1), 51–61.CrossRef Hassoun, M. H., & Song, J. (1992). Adaptive Ho-Kashyap rules for perceptron training. IEEE Transactions on Neural Networks, 3(1), 51–61.CrossRef
23.
Zurück zum Zitat Ho, Y. C., & Kashyap, R. L. (1965). An algorithm for linear inequalities and its applications. IEEE Transactions of Electronic Computers, 14, 683–688.MATHCrossRef Ho, Y. C., & Kashyap, R. L. (1965). An algorithm for linear inequalities and its applications. IEEE Transactions of Electronic Computers, 14, 683–688.MATHCrossRef
24.
Zurück zum Zitat Ho, C. Y.-F., Ling, B. W.-K., Lam, H.-K., & Nasir, M. H. U. (2008). Global convergence and limit cycle behavior of weights of perceptron. IEEE Transactions on Neural Networks, 19(6), 938–947.CrossRef Ho, C. Y.-F., Ling, B. W.-K., Lam, H.-K., & Nasir, M. H. U. (2008). Global convergence and limit cycle behavior of weights of perceptron. IEEE Transactions on Neural Networks, 19(6), 938–947.CrossRef
25.
Zurück zum Zitat Ho, C. Y.-F., Ling, B. W.-K., & Iu, H. H.-C. (2010). Invariant set of weight of perceptron trained by perceptron training algorithm. IEEE Transactions on Systems, Man, and Cybernetics Part B, 40(6), 1521–1530.CrossRef Ho, C. Y.-F., Ling, B. W.-K., & Iu, H. H.-C. (2010). Invariant set of weight of perceptron trained by perceptron training algorithm. IEEE Transactions on Systems, Man, and Cybernetics Part B, 40(6), 1521–1530.CrossRef
26.
Zurück zum Zitat Khardon, R., & Wachman, G. (2007). Noise tolerant variants of the perceptron algorithm. Journal of Machine Learning Research, 8, 227–248.MATH Khardon, R., & Wachman, G. (2007). Noise tolerant variants of the perceptron algorithm. Journal of Machine Learning Research, 8, 227–248.MATH
27.
Zurück zum Zitat Kivinen, J., Smola, A. J., & Williamson, R. C. (2004). Online learning with kernels. IEEE Transactions on Signal Processing, 52(8), 2165–2176.MathSciNetMATHCrossRef Kivinen, J., Smola, A. J., & Williamson, R. C. (2004). Online learning with kernels. IEEE Transactions on Signal Processing, 52(8), 2165–2176.MathSciNetMATHCrossRef
28.
Zurück zum Zitat Krauth, W., & Mezard, M. (1987). Learning algorithms with optimal stability in neural networks. Journal of Physics A, 20(11), 745–752.MathSciNetCrossRef Krauth, W., & Mezard, M. (1987). Learning algorithms with optimal stability in neural networks. Journal of Physics A, 20(11), 745–752.MathSciNetCrossRef
29.
Zurück zum Zitat Legenstein, R., & Maass, W. (2008). On the classification capability of sign-constrained perceptrons. Neural Computation, 20, 288–309.MathSciNetMATHCrossRef Legenstein, R., & Maass, W. (2008). On the classification capability of sign-constrained perceptrons. Neural Computation, 20, 288–309.MathSciNetMATHCrossRef
30.
Zurück zum Zitat Li, Y., & Long, P. (2002). The relaxed online maximum margin algorithm. Machine Learning, 46, 361–387.MATHCrossRef Li, Y., & Long, P. (2002). The relaxed online maximum margin algorithm. Machine Learning, 46, 361–387.MATHCrossRef
31.
Zurück zum Zitat Mansfield, A. J. (1991). Training perceptrons by linear programming. NPL Report DITC 181/91, National Physical Laboratory, Teddington, Middlesex, UK. Mansfield, A. J. (1991). Training perceptrons by linear programming. NPL Report DITC 181/91, National Physical Laboratory, Teddington, Middlesex, UK.
32.
Zurück zum Zitat Maass, W., Natschlaeger, T., & Markram, H. (2002). Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation, 14(11), 2531–2560.MATHCrossRef Maass, W., Natschlaeger, T., & Markram, H. (2002). Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation, 14(11), 2531–2560.MATHCrossRef
33.
Zurück zum Zitat Mays, C. H. (1963). Adaptive threshold logic. PhD thesis, Stanford University. Mays, C. H. (1963). Adaptive threshold logic. PhD thesis, Stanford University.
34.
Zurück zum Zitat Muselli, M. (1997). On convergence properties of pocket algorithm. IEEE Transactions on Neural Networks, 8(3), 623–629.MathSciNetCrossRef Muselli, M. (1997). On convergence properties of pocket algorithm. IEEE Transactions on Neural Networks, 8(3), 623–629.MathSciNetCrossRef
35.
Zurück zum Zitat Nagaraja, G., & Bose, R. P. J. C. (2006). Adaptive conjugate gradient algorithm for perceptron training. Neurocomputing, 69, 368–386.CrossRef Nagaraja, G., & Bose, R. P. J. C. (2006). Adaptive conjugate gradient algorithm for perceptron training. Neurocomputing, 69, 368–386.CrossRef
36.
Zurück zum Zitat Panagiotakopoulos, C., & Tsampouka, P. (2011). The Margitron: A generalized perceptron with margin. IEEE Transactions on Neural Networks, 22(3), 395–407.MATHCrossRef Panagiotakopoulos, C., & Tsampouka, P. (2011). The Margitron: A generalized perceptron with margin. IEEE Transactions on Neural Networks, 22(3), 395–407.MATHCrossRef
37.
Zurück zum Zitat Perantonis, S. J., & Virvilis, V. (2000). Efficient perceptron learning using constrained steepest descent. Neural Networks, 13(3), 351–364.CrossRef Perantonis, S. J., & Virvilis, V. (2000). Efficient perceptron learning using constrained steepest descent. Neural Networks, 13(3), 351–364.CrossRef
38.
Zurück zum Zitat Rosenblatt, R. (1958). The Perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65, 386–408.CrossRef Rosenblatt, R. (1958). The Perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65, 386–408.CrossRef
39.
Zurück zum Zitat Rosenblatt, R. (1962). Principles of neurodynamics. New York: Spartan Books.MATH Rosenblatt, R. (1962). Principles of neurodynamics. New York: Spartan Books.MATH
40.
Zurück zum Zitat Rowcliffe, P., Feng, J., & Buxton, H. (2006). Spiking Perceptrons. IEEE Transactions on Neural Networks, 17(3), 803–807.CrossRef Rowcliffe, P., Feng, J., & Buxton, H. (2006). Spiking Perceptrons. IEEE Transactions on Neural Networks, 17(3), 803–807.CrossRef
41.
Zurück zum Zitat Shalev-Shwartz, S. & Singer, Y. (2005). A new perspective on an old perceptron algorithm. In: Proceedings of the 16th Annual Conference on Computational Learning Theory (pp. 264–278). Shalev-Shwartz, S. & Singer, Y. (2005). A new perspective on an old perceptron algorithm. In: Proceedings of the 16th Annual Conference on Computational Learning Theory (pp. 264–278).
42.
Zurück zum Zitat Sima, J. (2002). Training a single sigmoidal neuron Is hard. Neural Computation, 14, 2709–2728.MATHCrossRef Sima, J. (2002). Training a single sigmoidal neuron Is hard. Neural Computation, 14, 2709–2728.MATHCrossRef
43.
Zurück zum Zitat Vallet, F. (1989). The Hebb rule for learning linearly separable Boolean functions: learning and generalisation. Europhysics Letters, 8(8), 747–751.CrossRef Vallet, F. (1989). The Hebb rule for learning linearly separable Boolean functions: learning and generalisation. Europhysics Letters, 8(8), 747–751.CrossRef
44.
Zurück zum Zitat Werbos, P. J. (1990). Backpropagation through time: What it does and how to do it. Proceedings of the IEEE, 78(10), 1550–1560.CrossRef Werbos, P. J. (1990). Backpropagation through time: What it does and how to do it. Proceedings of the IEEE, 78(10), 1550–1560.CrossRef
45.
Zurück zum Zitat Widrow, B. & Hoff, M. E. (1960). Adaptive switching circuits. In Record of IRE Eastern Electronic Show & Convention (WESCON) (Vol. 4, pp. 96–104). Widrow, B. & Hoff, M. E. (1960). Adaptive switching circuits. In Record of IRE Eastern Electronic Show & Convention (WESCON) (Vol. 4, pp. 96–104).
46.
Zurück zum Zitat Widrow, B., & Lehr, M. A. (1990). 30 years of adaptive neural networks: Perceptron, Madaline, and backpropagation. Proceedings of the IEEE, 78(9), 1415–1442.CrossRef Widrow, B., & Lehr, M. A. (1990). 30 years of adaptive neural networks: Perceptron, Madaline, and backpropagation. Proceedings of the IEEE, 78(9), 1415–1442.CrossRef
Metadaten
Titel
Perceptrons
verfasst von
Ke-Lin Du
M. N. S. Swamy
Copyright-Jahr
2019
Verlag
Springer London
DOI
https://doi.org/10.1007/978-1-4471-7452-3_4