Skip to main content
SpringerLink
Log in

Deep and Modular Neural Networks

  • Chapter
Springer Handbook of Computational Intelligence

Part of the book series: Springer Handbooks ((SHB))

Abstract

In this chapter, we focus on two important areas in neural computation, i. e., deep and modular neural networks, given the fact that both deep and modular neural networks are among the most powerful machine learning and pattern recognition techniques for complex GlossaryTerm

AI

problem solving. We begin by providing a general overview of deep and modular neural networks to describe the general motivation behind such neural architectures and fundamental requirements imposed by complex GlossaryTerm

AI

problems. Next, we describe background and motivation, methodologies, major building blocks, and the state-of-the-art hybrid learning strategy in context of deep neural architectures. Then, we describe background and motivation, taxonomy, and learning algorithms pertaining to various typical modular neural networks in a wide context. Furthermore, we also examine relevant issues and discuss open problems in deep and modular neural network research areas.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 269.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 349.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Abbreviations

AI:

artificial intelligence

BP:

back-propagation

CAE:

contrastive auto-encoder

CD:

contrastive divergence

CNS:

central nervous system

DAE:

denoising auto-encoder

DBN:

deep belief network

DNN:

deep neural network

EM:

expectation maximization

FMM:

finite mixture model

GPU:

graphics processing unit

GRBM:

Gaussian RBM

IRLS:

iteratively re-weighted least squares

ML:

machine learning

MLP:

multilayer perceptron

MNN:

modular neural network

MoE:

mixture of experts

MSE:

mean square error

NCL:

negative correlation learning

NC:

neural computation

NN:

neural network

PoE:

product of experts

PSD:

predictive sparse decomposition

RBF:

radial basis function

RBM:

Boltzmann machine

SAE:

sparse auto-encoder

SVM:

support vector machine

References

  1. E.R. Kandel, J.H. Schwartz, T.M. Jessell: Principle of Neural Science, 4th edn. (McGraw-Hill, New York 2000)

    Google Scholar 

  2. G.M. Edelman: Neural Darwinism: Theory of Neural Group Selection (Basic Books, New York 1987)

    Google Scholar 

  3. J.A. Fodor: The Modularity of Mind (MIT Press, Cambridge 1983)

    Google Scholar 

  4. F. Azam: Biologically inspired modular neural networks, Ph.D. Thesis (School of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, Blacksburg 2000)

    Google Scholar 

  5. G. Auda, M. Kamel: Modular neural networks: A survey, Int. J. Neural Syst. 9(2), 129–151 (1999)

    Article  Google Scholar 

  6. D.C. Van Essen, C.H. Anderson, D.J. Fellman: Information processing in the primate visual system, Science 255, 419–423 (1992)

    Article  Google Scholar 

  7. J.H. Kaas: Why does the brain have so many visual areas?, J. Cogn. Neurosci. 1(2), 121–135 (1989)

    Article  Google Scholar 

  8. G. Bugmann: Biologically plausible neural computation, Biosystems 40(1), 11–19 (1997)

    Article  Google Scholar 

  9. S. Haykin: Neural Networks and Learning Machines, 3rd edn. (Prentice Hall, New York 2009)

    Google Scholar 

  10. M. Minsky, S. Papert: Perceptrons (MIT Press, Cambridge 1969)

    MATH  Google Scholar 

  11. D.E. Rumelhurt, G.E. Hinton, R.J. Williams: Learning internal representations by error propagation, Nature 323, 533–536 (1986)

    Article  Google Scholar 

  12. Y. LeCun, L. Bottou, Y. Bengio, P. Haffner: Gradient based learning applied to document recognition, Proc. IEEE 86(9), 2278–2324 (1998)

    Article  Google Scholar 

  13. G. Tesauro: Practical issues in temporal difference learning, Mach. Learn. 8(2), 257–277 (1992)

    MATH  Google Scholar 

  14. G. Cybenko: Approximations by superpositions of sigmoidal functions, Math. Control Signals Syst. 2(4), 302–314 (1989)

    Article  MathSciNet  MATH  Google Scholar 

  15. N. Cristianini, J. Shawe-Taylor: An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods (Cambridge University Press, Cambridge 2000)

    Book  MATH  Google Scholar 

  16. Y. Bengio, Y. LeCun: Scaling learning algorithms towards AI. In: Large-Scale Kernel Machines, ed. by L. Bottou, O. Chapelle, D. DeCoste, J. Weston (MIT Press, Cambridge 2006), Chap. 14

    Google Scholar 

  17. Y. Bengio: Learning deep architectures for AI, Found. Trends Mach. Learn. 2(1), 1–127 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  18. G.E. Hinton, S. Osindero, Y. Teh: A fast learning algorithm for deep belief nets, Neural Comput. 18(9), 1527–1554 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  19. Y. Bengio: Deep learning of representations for unsupervised and transfer learning, JMLR: Workshop Conf. Proc., Vol. 7 (2011) pp. 1–20

    Google Scholar 

  20. H. Larochelle, D. Erhan, A. Courville, J. Bergstra, Y. Bengio: An empirical evaluation of deep architectures on problems with many factors of variation, Proc. Int. Conf. Mach. Learn. (ICML) (2007) pp. 473–480

    Google Scholar 

  21. R. Salakhutdinov, G.E. Hinton: Learning a nonlinear embedding by preserving class neighbourhood structure, Proc. Int. Conf. Artif. Intell. Stat. (AISTATS) (2007)

    Google Scholar 

  22. H. Larochelle, Y. Bengio, J. Louradour, P. Lamblin: Exploring strategies for training deep neural networks, J. Mach. Learn. Res. 10(1), 1–40 (2009)

    MATH  Google Scholar 

  23. W.K. Wong, M. Sun: Deep learning regularized Fisher mappings, IEEE Trans. Neural Netw. 22(10), 1668–1675 (2011)

    Article  Google Scholar 

  24. S. Osindero, G.E. Hinton: Modeling image patches with a directed hierarchy of Markov random field, Adv. Neural Inf. Process. Syst. (NIPS) (2007) pp. 1121–1128

    Google Scholar 

  25. I. Levner: Data driven object segmentation, Ph.D. Thesis (Department of Computer Science, University of Alberta, Edmonton 2008)

    Google Scholar 

  26. H. Mobahi, R. Collobert, J. Weston: Deep learning from temporal coherence in video, Proc. Int. Conf. Mach. Learn. (ICML) (2009) pp. 737–744

    Google Scholar 

  27. H. Lee, Y. Largman, P. Pham, A. Ng: Unsupervised feature learning for audio classification using convolutional deep belief networks, Adv. Neural Inf. Process. Syst. (NIPS) (2009)

    Google Scholar 

  28. K. Chen, A. Salman: Learning speaker-specific characteristics with a deep neural architecture, IEEE Trans. Neural Netw. 22(11), 1744–1756 (2011)

    Article  Google Scholar 

  29. K. Chen, A. Salman: Extracting speaker-specific information with a regularized Siamese deep network, Adv. Neural Inf. Process. Syst. (NIPS) (2011)

    Google Scholar 

  30. A. Mohamed, G.E. Dahl, G.E. Hinton: Acoustic modeling using deep belief networks, IEEE Trans. Audio Speech Lang. Process. 20(1), 14–22 (2012)

    Article  Google Scholar 

  31. G.E. Dahl, D. Yu, L. Deng, A. Acero: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition, IEEE Trans. Audio Speech Lang. Process. 20(1), 30–42 (2012)

    Article  Google Scholar 

  32. R. Salakhutdinov, G.E. Hinton: Semantic hashing, Proc. SIGIR Workshop Inf. Retr. Appl. Graph. Model. (2007)

    Google Scholar 

  33. M. Ranzato, M. Szummer: Semi-supervised learning of compact document representations with deep networks, Proc. Int. Conf. Mach. Learn. (ICML) (2008)

    Google Scholar 

  34. A. Torralba, R. Fergus, Y. Weiss: Small codes and large databases for recognition, Proc. Int. Conf. Comput. Vis. Pattern Recogn. (CVPR) (2008) pp. 1–8

    Google Scholar 

  35. R. Collobert, J. Weston: A unified architecture for natural language processing: Deep neural networks with multitask learning, Proc. Int. Conf. Mach. Learn. (ICML) (2008)

    Google Scholar 

  36. A. Mnih, G.E. Hinton: A scalable hierarchical distributed language model, Adv. Neural Inf. Process. Syst. (NIPS) (2008)

    Google Scholar 

  37. J. Weston, F. Ratle, R. Collobert: Deep learning via semi-supervised embedding, Proc. Int. Conf. Mach. Learn. (ICML) (2008)

    Google Scholar 

  38. R. Hadsell, A. Erkan, P. Sermanet, M. Scoffier, U. Muller, Y. LeCun: Deep belief net learning in a long-range vision system for autonomous offroad driving, Proc. Intell. Robots Syst. (IROS) (2008) pp. 628–633

    Google Scholar 

  39. Y. Bengio, A. Courville, P. Vincent: Representation learning: A review and new perspectives, IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1827 (2013)

    Article  Google Scholar 

  40. Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle: Greedy layer-wise training of deep networks, Adv. Neural Inf. Process. Syst. (NIPS) (2006)

    Google Scholar 

  41. P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, P.A. Manzagol: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion, J. Mach. Learn. Res. 11, 3371–3408 (2010)

    MathSciNet  MATH  Google Scholar 

  42. G.E. Hinton: Training products of experts by minimizing contrastive divergence, Neural Comput. 14(10), 1771–1800 (2002)

    Article  MathSciNet  MATH  Google Scholar 

  43. K. Kavukcuoglu, M. Ranzato, Y. LeCun: Fast inference in sparse coding algorithms with applications to object recognition. CoRR, arXiv:1010.3467 (2010)

    Google Scholar 

  44. B.A. Olshausen, D.J. Field: Sparse coding with an overcomplete basis set: A strategy employed by V1?, Vis. Res. 37, 3311–3325 (1997)

    Article  Google Scholar 

  45. S. Rifai, P. Vincent, X. Muller, X. Glorot, Y. Bengio: Contracting auto-encoders: Explicit invariance during feature extraction, Proc. Int. Conf. Mach. Learn. (ICML) (2011)

    Google Scholar 

  46. S. Rifai, G. Mesnil, P. Vincent, X. Muller, Y. Bengio, Y. Dauphin, X. Glorot: Higher order contractive auto-encoder, Proc. Eur. Conf. Mach. Learn. (ECML) (2011)

    Google Scholar 

  47. M. Ranzato, C. Poultney, S. Chopra, Y. LeCun: Efficient learning of sparse representations with an energy based model, Adv. Neural Inf. Process. Syst. (NIPS) (2006)

    Google Scholar 

  48. M. Ranzato, Y. Boureau, Y. LeCun: Sparse feature learning for deep belief networks, Adv. Neural Inf. Process. Syst. (NIPS) (2007)

    Google Scholar 

  49. G.E. Hinton, R. Salakhutdinov: Reducing the dimensionality of data with neural networks, Science 313, 504–507 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  50. K. Cho, A. Ilin, T. Raiko: Improved learning of Gaussian-Bernoulli restricted Boltzmann machines, Proc. Int. Conf. Artif. Neural Netw. (ICANN) (2011)

    Google Scholar 

  51. D. Erhan, Y. Bengio, A. Courville, P.A. Manzagol, P. Vincent, S. Bengio: Why does unsupervised pretraining help deep learning?, J. Mach. Learn. Res. 11, 625–660 (2010)

    MathSciNet  MATH  Google Scholar 

  52. D.C. Ciresan, U. Meier, L.M. Gambardella, J. Schmidhuber: Deep big simple neural nets for handwritten digit recognition, Neural Comput. 22(1), 1–14 (2010)

    Article  MathSciNet  Google Scholar 

  53. M. Ranzato, A. Krizhevsky, G.E. Hinton: Factored 3-way restricted Boltzmann machines for modeling natural images, Proc. Int. Conf. Artif. Intell. Stat. (AISTATS) (2010) pp. 621–628

    Google Scholar 

  54. M. Ranzato, V. Mnih, G.E. Hinton: Generating more realistic images using gated MRF's, Adv. Neural Inf. Process. Syst. (NIPS) (2010)

    Google Scholar 

  55. A. Courville, J. Bergstra, Y. Bengio: Unsupervised models of images by spike-and-slab RBMs, Proc. Int. Conf. Mach. Learn. (ICML) (2011)

    Google Scholar 

  56. H. Lee, R. Grosse, R. Ranganath, A.Y. Ng: Unsupervised learning of hierarchical representations with convolutional deep belief networks, Commun. ACM 54(10), 95–103 (2011)

    Article  Google Scholar 

  57. D. Hau, K. Chen: Exploring hierarchical speech representations with a deep convolutional neural network, Proc. U.K. Workshop Comput. Intell. (UKCI) (2011)

    Google Scholar 

  58. Q. Le, M. Ranzato, R. Monga, M. Devin, K. Chen, G.S. Corrado, J. Dean, A.Y. Ng: Building high-level features using large scale unsupervised learning, Proc. Int. Conf. Mach. Learn. (ICML) (2012)

    Google Scholar 

  59. S.E. Yuksel, J.N. Wilson, P.D. Gader: Twenty years of mixture of experts, IEEE Trans. Neural Netw. Learn. Syst. 23(8), 1177–1193 (2012)

    Article  Google Scholar 

  60. A. Krogh, J. Vedelsby: Neural network ensembles, cross validation, and active learning, Adv. Neural Inf. Process. Syst. (NIPS) (1995)

    Google Scholar 

  61. N. Ueda, R. Nakano: Generalization error of ensemble estimators, Proc. Int. Conf. Neural Netw. (ICNN) (1996) pp. 90–95

    Chapter  Google Scholar 

  62. L.I. Kuncheva: Combining Pattern Classifiers (Wiley-Interscience, Hoboken 2004)

    Book  MATH  Google Scholar 

  63. R.A. Jacobs, M.I. Jordan, S. Nowlan, G.E. Hinton: Adaptive mixture of local experts, Neural Comput. 3(1), 79–87 (1991)

    Article  Google Scholar 

  64. M.I. Jordan, R.A. Jacobs: Hierarchical mixture of experts and the EM algorithm, Neural Comput. 6(2), 181–214 (1994)

    Article  Google Scholar 

  65. Y. Liu, X. Yao: Simultaneous training of negatively correlated neural networks in an ensemble, IEEE Trans. Syst. Man Cybern. B 29(6), 716–725 (1999)

    Article  Google Scholar 

  66. K. Chen, L. Xu, H.S. Chi: Improved learning algorithms for mixture of experts in multi-class classification, Neural Netw. 12(9), 1229–1252 (1999)

    Article  Google Scholar 

  67. L.K. Hansen, P. Salamon: Neural network ensembles, IEEE Trans. Pattern Anal. Mach. Intell. 12(10), 993–1001 (1990)

    Article  Google Scholar 

  68. M.P. Perrone, L.N. Cooper: Ensemble methods for hybrid neural networks. In: Artificial Neural Networks for Speech and Vision, ed. by R.J. Mammone (Chapman-Hall, New York 1993) pp. 126–142

    Google Scholar 

  69. T.K. Ho: The random subspace method for constructing decision forests, IEEE Trans. Pattern Anal. Mach. Intell. 20(8), 823–844 (1998)

    Google Scholar 

  70. K. Chen, L. Wang, H.S. Chi: Methods of combining multiple classifiers with different feature sets and their applications to text-independent speaker identification, Int. J. Pattern Recogn. Artif. Intell. 11(3), 417–445 (1997)

    Article  Google Scholar 

  71. J. Kittler, M. Hatef, R.P.W. Duin, J. Matas: On combining classifiers, IEEE Trans. Pattern Anal. Mach. Intell. 20(3), 226–239 (1998)

    Article  Google Scholar 

  72. D.H. Wolpert: Stacked generalization, Neural Netw. 2(3), 241–259 (1992)

    Article  MathSciNet  Google Scholar 

  73. L. Xu, M.I. Jordan, G.E. Hinton: An alternative model for mixtures of experts, Adv. Neural Inf. Process. Syst. (NIPS) (1995)

    Google Scholar 

  74. L. Xu, A. Krzyzak, C.Y. Suen: Associative switch for combining multiple classifiers, J. Artif. Neural Netw. 1(1), 77–100 (1994)

    Google Scholar 

  75. K. Chen: A connectionist method for pattern classification with diverse feature sets, Pattern Recogn. Lett. 19(7), 545–558 (1998)

    Article  MATH  Google Scholar 

  76. K. Chen, H.S. Chi: A method of combining multiple probabilistic classifiers through soft competition on different feature sets, Neurocomputing 20(1–3), 227–252 (1998)

    Article  MATH  Google Scholar 

  77. K. Chen: On the use of different representations for speaker modeling, IEEE Trans. Syst. Man Cybern. C 35(3), 328–346 (2005)

    Article  Google Scholar 

  78. Y. Yang, K. Chen: Temporal data clustering via weighted clustering ensemble with different representations, IEEE Trans. Knowl. Data Eng. 23(2), 307–320 (2011)

    Article  Google Scholar 

  79. Y. Yang, K. Chen: Time series clustering via RPCL ensemble networks with different representations, IEEE Trans. Syst. Man Cybern. C 41(2), 190–199 (2011)

    Article  Google Scholar 

  80. L. Xu, A. Krzyzak, C.Y. Suen: Methods of combining multiple classifiers and their applications to handwriting recognition, IEEE Trans. Syst. Man Cybern. 22(3), 418–435 (1992)

    Article  Google Scholar 

  81. K. Chen, X. Yu, H.S. Chi: Combining linear discriminant functions with neural networks for supervised learning, Neural Comput. Appl. 6(1), 19–41 (1997)

    Article  Google Scholar 

  82. K. Chen, L.P. Yang, X. Yu, H.S. Chi: A self-generating modular neural network architecture for supervised learning, Neurocomputing 16(1), 33–48 (1997)

    Article  Google Scholar 

  83. B.L. Lu, M. Ito: Task decomposition and module combination based on class relations: A modular neural network for pattern classification, IEEE Trans. Neural Netw. Learn. Syst. 10(5), 1244–1256 (1999)

    Article  Google Scholar 

  84. L. Cao: Support vector machines experts for time series forecasting, Neurocomputing 51(3), 321–339 (2003)

    Google Scholar 

  85. T.G. Dietterich: Ensemble learning. In: Handbook of Brain Theory and Neural Networks, ed. by M.A. Arbib (MIT Press, Cambridge 2002) pp. 405–408

    Google Scholar 

  86. Y. Freund, R.E. Schapire: Experiments with a new boosting algorithm, Proc. Int. Conf. Mach. Learn. (ICML) (1996) pp. 148–156

    Google Scholar 

  87. L. Breiman: Bagging predictors, Mach. Learn. 24(2), 123–140 (1996)

    MathSciNet  MATH  Google Scholar 

  88. H. Schwenk, Y. Bengio: Boosting neural networks, Neural Comput. 12(8), 1869–1887 (2000)

    Article  Google Scholar 

  89. J. Wang, V. Saligrama: Local supervised learning through space partitioning, Adv. Neural Inf. Process. Syst. (NIPS) (2012)

    Google Scholar 

  90. X.J. Zhu: Semi-supervised learning literature survey, Technical Report, School of Computer Science (University of Wisconsin, Madison 2008)

    Google Scholar 

  91. J. Ghosh, A. Acharya: Cluster ensembles, WIREs Data Min. Knowl. Discov. 1(2), 305–315 (2011)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science, The University of Manchester, G10 Kilburn Building, Oxford Road, M13 9PL, Manchester, UK

    Ke Chen

Authors
  1. Ke Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ke Chen .

Editor information

Editors and Affiliations

  1. Systems Research Inst., Polish Academy of Sciences, ul. Newelska 6, 01-447, Warsaw, Poland

    Janusz Kacprzyk

  2. Dep. Electrical and Computer Engineering, University of Alberta, 116 Street 9107, T6J 2V4, Edmonton, Alberta, Canada

    Witold Pedrycz

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Chen, K. (2015). Deep and Modular Neural Networks. In: Kacprzyk, J., Pedrycz, W. (eds) Springer Handbook of Computational Intelligence. Springer Handbooks. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-43505-2_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-662-43505-2_28

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-662-43504-5

  • Online ISBN: 978-3-662-43505-2

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation