Article

Modular learning in neural networks

Author:

AAAI'87: Proceedings of the sixth National conference on Artificial intelligence - Volume 1

Pages 279 - 284

Published: 13 July 1987 Publication History

Abstract

In the development of large-scale knowledge networks much recent progress has been inspired by connections to neurobiology. An important component of any "neural" network is an accompanying learning algorithm. Such an algorithm, to be biologically plausible, must work for very large numbers of units. Studies of large-scale systems have so far been restricted to systems Without internal units (units With no direct connections to the input or output). Internal units are crucial to such systems as they are the means by which a system can encode high-order regularities (or invariants) that are Implicit in its inputs and outputs. Computer simulations of learning using internal units have been restricted to small-scale systems. This paper describes away of coupling autoassociative learning modules Into hierarchies that should greatly improve the performance of learning algorithms in large-scale systems. The Idea has been tested experimentally with positive results.

References

[1]

Ackley, D.H., G.E. Hinton, and T.J. Sejnowski, "A learning algorithm for Boltzmann machines," Cognitive Science 9, 1, 147-169, January-March 1985.

Google Scholar

[2]

Barlow, H.B., "Single units and sensation: A neuron doctrine for perceptual psychology?," Perception 1, 371- 394,1972.

Google Scholar

[3]

Baum, E., J. Moody, and F. Wilczek, "Internal representations for content addressable memory," Technical Report, Inst. for Theoretical Physics, U. California, Santa Barbara, December 1986.

Google Scholar

[4]

Feldman, J.A., "Dynamic connections in neural networks," Biological Cybernetics 46, 27-39, 1982.

Google Scholar

[5]

Lapedes, A. and R. Farber, "Programming a massively parallel, computation universal system: Static behavior," Proc., Snowbird Conf. on Neural Nets and Computation, April 1986.

Crossref

Google Scholar

[6]

Pearlmutter, B.A. and G.E. Hinton, "Maximization: An unsupervised learning procedure for discovering regularities," Technical Report, Carnegie Mellon U., May 1986.

Google Scholar

[7]

Rumelhart, D.E. and D. Zipser, "Feature discovery by competitive learning", Cognitive Science 9, 1, 75-112, January-March 1985.

Google Scholar

[8]

Rumelhart, D.E., G.E. Hinton, and R.J. Williams, "Learning internal representations by error propagation", in D.E. Rumelhart and J.L. McClelland. (Eds). Parallel Distributed Processing. MIT Press, pp. 318-364, 1986.

Crossref

Google Scholar

[9]

Scalettar, R. and A. Zee, "A feedforward memory with decay," Technical Report NSF-ITP-86-118, Inst. for Theoretical Physics, U. California, Santa Barbara, 1986.

Google Scholar

[10]

Zipser, D., "Programming networks to compute spatial functions," ICS Report 8608, Inst. for Cognitive Science, U. California, San Diego, La Jolla, June 1986.

Google Scholar

Cited By

View all

Chen YHwang RChen MWen CHsu C(2021)Screw Slot Quality Inspection System Based on Tactile NetworkACM Transactions on Internet Technology10.1145/342355621:4(1-17)Online publication date: 22-Jul-2021
https://dl.acm.org/doi/10.1145/3423556
Wu GLuo KSanner SSoh HBogers TSaid ABrusilovsky PTikk D(2019)Deep language-based critiquing for recommender systemsProceedings of the 13th ACM Conference on Recommender Systems10.1145/3298689.3347009(137-145)Online publication date: 10-Sep-2019
https://dl.acm.org/doi/10.1145/3298689.3347009
Ota KDao MMezaris VNatale F(2017)Deep Learning for Mobile MultimediaACM Transactions on Multimedia Computing, Communications, and Applications10.1145/309283113:3s(1-22)Online publication date: 28-Jun-2017
https://dl.acm.org/doi/10.1145/3092831
Show More Cited By

Index Terms

Modular learning in neural networks
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Neural networks

Index terms have been assigned to the content through auto-classification.

Recommendations

Modular learning in neural networks
AAAI'87: Proceedings of the sixth National conference on Artificial intelligence - Volume 1

In the development of large-scale knowledge networks much recent progress has been inspired by connections to neurobiology. An important component of any "neural" network is an accompanying learning algorithm. Such an algorithm, to be biologically ...
Modular Learning in Neural Networks: A Modularized Approach to Neural Network Classification
A Reinforcement Learning Algorithm for Spiking Neural Networks
SYNASC '05: Proceedings of the Seventh International Symposium on Symbolic and Numeric Algorithms for Scientific Computing

The paper presents a new reinforcement learning mechanism for spiking neural networks. The algorithm is derived for networks of stochastic integrate-and-fire neurons, but it can be also applied to generic spiking neural networks. Learning is achieved by ...

Comments

Information & Contributors

Information

Published In

AAAI'87: Proceedings of the sixth National conference on Artificial intelligence - Volume 1

July 1987

835 pages

ISBN:0934613427

Publisher

AAAI Press

Publication History

Published: 13 July 1987

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Chen YHwang RChen MWen CHsu C(2021)Screw Slot Quality Inspection System Based on Tactile NetworkACM Transactions on Internet Technology10.1145/342355621:4(1-17)Online publication date: 22-Jul-2021
https://dl.acm.org/doi/10.1145/3423556
Wu GLuo KSanner SSoh HBogers TSaid ABrusilovsky PTikk D(2019)Deep language-based critiquing for recommender systemsProceedings of the 13th ACM Conference on Recommender Systems10.1145/3298689.3347009(137-145)Online publication date: 10-Sep-2019
https://dl.acm.org/doi/10.1145/3298689.3347009
Ota KDao MMezaris VNatale F(2017)Deep Learning for Mobile MultimediaACM Transactions on Multimedia Computing, Communications, and Applications10.1145/309283113:3s(1-22)Online publication date: 28-Jun-2017
https://dl.acm.org/doi/10.1145/3092831
Schmidhuber J(2015)Deep learning in neural networksNeural Networks10.1016/j.neunet.2014.09.00361:C(85-117)Online publication date: 1-Jan-2015
https://dl.acm.org/doi/10.1016/j.neunet.2014.09.003

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations