Skip to main content

2017 | OriginalPaper | Buchkapitel

Lie Algebra-Valued Bidirectional Associative Memories

verfasst von : Călin-Adrian Popa

Erschienen in: Recent Advances in Soft Computing

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

In recent years, complex-, quaternion-, and Clifford-valued neural networks have been intensively studied. This paper introduces Lie algebra-valued bidirectional associative memories, an alternative generalization of the real-valued neural networks, for which the states, outputs, and thresholds are all from a Lie algebra. The definition of these networks is given, together with an expression for an energy function, that is indeed proven to be an energy function for the proposed network.

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 Arena, P., Fortuna, L., Muscato, G., Xibilia, M.: Multilayer perceptrons to approximate quaternion valued functions. Neural Networks 10(2), 335–342 (1997)CrossRef Arena, P., Fortuna, L., Muscato, G., Xibilia, M.: Multilayer perceptrons to approximate quaternion valued functions. Neural Networks 10(2), 335–342 (1997)CrossRef
2.
Zurück zum Zitat Arena, P., Fortuna, L., Occhipinti, L., Xibilia, M.: Neural networks for quaternion valued function approximation. In: International Symposium on Circuits and Systems (ISCAS), vol. 6, pp. 307–310. IEEE (1994) Arena, P., Fortuna, L., Occhipinti, L., Xibilia, M.: Neural networks for quaternion valued function approximation. In: International Symposium on Circuits and Systems (ISCAS), vol. 6, pp. 307–310. IEEE (1994)
3.
Zurück zum Zitat Buchholz, S., Sommer, G.: On clifford neurons and clifford multi-layer perceptrons. Neural Networks 21(7), 925–935 (2008)CrossRefMATH Buchholz, S., Sommer, G.: On clifford neurons and clifford multi-layer perceptrons. Neural Networks 21(7), 925–935 (2008)CrossRefMATH
4.
Zurück zum Zitat Hirose, A.: Complex-Valued Neural Networks. Studies in Computational Intelligence, vol. 400. Springer, Heidelberg (2012)MATH Hirose, A.: Complex-Valued Neural Networks. Studies in Computational Intelligence, vol. 400. Springer, Heidelberg (2012)MATH
5.
Zurück zum Zitat Iachello, F.: Lie Algebras and Applications. Lecture Notes in Physics, vol. 891. Springer, Heidelberg (2015)MATH Iachello, F.: Lie Algebras and Applications. Lecture Notes in Physics, vol. 891. Springer, Heidelberg (2015)MATH
6.
Zurück zum Zitat de Kerf, E., Bauerle, G., ten Kroode, A.: Lie Algebras: Finite and Infinite Dimensional Lie Algebras and Applications in Physics. North Holland, Amsterdam (1997)MATH de Kerf, E., Bauerle, G., ten Kroode, A.: Lie Algebras: Finite and Infinite Dimensional Lie Algebras and Applications in Physics. North Holland, Amsterdam (1997)MATH
8.
Zurück zum Zitat Kuroe, Y.: Models of clifford recurrent neural networks and their dynamics. In: International Joint Conference on Neural Networks (IJCNN), pp. 1035–1041. IEEE (2011) Kuroe, Y.: Models of clifford recurrent neural networks and their dynamics. In: International Joint Conference on Neural Networks (IJCNN), pp. 1035–1041. IEEE (2011)
9.
Zurück zum Zitat Kuroe, Y., Tanigawa, S., Iima, H.: Models of Hopfield-type Clifford neural networks and their energy functions - hyperbolic and dual valued networks. In: Lu, B.-L., Zhang, L., Kwok, J. (eds.) ICONIP 2011. LNCS, vol. 7062, pp. 560–569. Springer, Heidelberg (2011). doi:10.1007/978-3-642-24955-6_67 CrossRef Kuroe, Y., Tanigawa, S., Iima, H.: Models of Hopfield-type Clifford neural networks and their energy functions - hyperbolic and dual valued networks. In: Lu, B.-L., Zhang, L., Kwok, J. (eds.) ICONIP 2011. LNCS, vol. 7062, pp. 560–569. Springer, Heidelberg (2011). doi:10.​1007/​978-3-642-24955-6_​67 CrossRef
10.
Zurück zum Zitat Lee, D., Wang, W.: A multivalued bidirectional associative memory operating on a complex domain. Neural Networks 11(9), 1623–1635 (1998)CrossRef Lee, D., Wang, W.: A multivalued bidirectional associative memory operating on a complex domain. Neural Networks 11(9), 1623–1635 (1998)CrossRef
11.
Zurück zum Zitat Mandic, D., Goh, S.: Complex Valued Nonlinear Adaptive Filters Noncircularity, Widely Linear and Neural Models. Wiley, Hoboken (2009)CrossRefMATH Mandic, D., Goh, S.: Complex Valued Nonlinear Adaptive Filters Noncircularity, Widely Linear and Neural Models. Wiley, Hoboken (2009)CrossRefMATH
12.
Zurück zum Zitat Nitta, T.: A back-propagation algorithm for neural networks based on 3d vector product. In: International Joint Conference on Neural Netwoks (IJCNN), vol. 1, pp. 589–592. IEEE (1993) Nitta, T.: A back-propagation algorithm for neural networks based on 3d vector product. In: International Joint Conference on Neural Netwoks (IJCNN), vol. 1, pp. 589–592. IEEE (1993)
13.
Zurück zum Zitat Nitta, T.: Generalization ability of the three-dimensional back-propagation network. In: International Conference on Neural Networks, vol. 5, pp. 2895–2900. IEEE (1994) Nitta, T.: Generalization ability of the three-dimensional back-propagation network. In: International Conference on Neural Networks, vol. 5, pp. 2895–2900. IEEE (1994)
14.
Zurück zum Zitat Nitta, T.: A quaternary version of the back-propagation algorithm. In: International Conference on Neural Networks, no. 5, pp. 2753–2756. IEEE (1995) Nitta, T.: A quaternary version of the back-propagation algorithm. In: International Conference on Neural Networks, no. 5, pp. 2753–2756. IEEE (1995)
15.
Zurück zum Zitat Nitta, T.: Three-dimensional vector valued neural network and its generalization ability. Neural Inf. Process. Lett. Rev. 10(10), 237–242 (2006) Nitta, T.: Three-dimensional vector valued neural network and its generalization ability. Neural Inf. Process. Lett. Rev. 10(10), 237–242 (2006)
16.
Zurück zum Zitat Nitta, T.: N-dimensional vector neuron. In: IJCAI Workshop on Complex-Valued Neural Networks and Neuro-Computing: Novel Methods, Applications and Implementations, pp. 2–7 (2007) Nitta, T.: N-dimensional vector neuron. In: IJCAI Workshop on Complex-Valued Neural Networks and Neuro-Computing: Novel Methods, Applications and Implementations, pp. 2–7 (2007)
17.
Zurück zum Zitat Nitta, T.: N-dimensional vector neuron and its application to the N-bit parity problem. In: Complex-Valued Neural Networks: Advances and Applications, pp. 59–74. Wiley (2013) Nitta, T.: N-dimensional vector neuron and its application to the N-bit parity problem. In: Complex-Valued Neural Networks: Advances and Applications, pp. 59–74. Wiley (2013)
18.
Zurück zum Zitat Pearson, J., Bisset, D.: Back propagation in a clifford algebra. In: International Conference on Artificial Neural Networks, vol. 2, pp. 413–416 (1992) Pearson, J., Bisset, D.: Back propagation in a clifford algebra. In: International Conference on Artificial Neural Networks, vol. 2, pp. 413–416 (1992)
19.
Zurück zum Zitat Pearson, J., Bisset, D.: Neural networks in the clifford domain. In: International Conference on Neural Networks, vol. 3, pp. 1465–1469. IEEE (1994) Pearson, J., Bisset, D.: Neural networks in the clifford domain. In: International Conference on Neural Networks, vol. 3, pp. 1465–1469. IEEE (1994)
20.
Zurück zum Zitat Popa, C.A.: Lie algebra-valued neural networks. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE, July 2015 Popa, C.A.: Lie algebra-valued neural networks. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE, July 2015
21.
Zurück zum Zitat Sattinger, D., Weaver, O.: Lie groups and algebras with applications to Physics, Geometry, and Mechanics. Applied Mathematical Sciences, vol. 61. Springer, New York (1986) Sattinger, D., Weaver, O.: Lie groups and algebras with applications to Physics, Geometry, and Mechanics. Applied Mathematical Sciences, vol. 61. Springer, New York (1986)
22.
Zurück zum Zitat Vallejo, J., Bayro-Corrochano, E.: Clifford hopfield neural networks. In: International Joint Conference on Neural Networks (IJCNN), pp. 3609–3612. IEEE, June 2008 Vallejo, J., Bayro-Corrochano, E.: Clifford hopfield neural networks. In: International Joint Conference on Neural Networks (IJCNN), pp. 3609–3612. IEEE, June 2008
23.
Zurück zum Zitat Widrow, B., McCool, J., Ball, M.: The complex lms algorithm. Proc. IEEE 63(4), 719–720 (1975)CrossRef Widrow, B., McCool, J., Ball, M.: The complex lms algorithm. Proc. IEEE 63(4), 719–720 (1975)CrossRef
24.
Zurück zum Zitat Xu, Q., Ma, D.: Applications of lie groups and lie algebra to computer vision a brief survey. In: International Conference on Systems and Informatics (ICSAI), pp. 2024–2029. IEEE, May 2012 Xu, Q., Ma, D.: Applications of lie groups and lie algebra to computer vision a brief survey. In: International Conference on Systems and Informatics (ICSAI), pp. 2024–2029. IEEE, May 2012
Metadaten
Titel
Lie Algebra-Valued Bidirectional Associative Memories
verfasst von
Călin-Adrian Popa
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-58088-3_12