This paper proposes the matrix modular neural network (MMNN), which is a modular neural network and adopts a novel task decomposition technique to solve complex problems, such as the large training sets and the category asymmetric training sets. A complex problem can be decomposed into many easier problems, each of which is dealt in two subspaces and can be solved by a single neural network module. All of these modules form a neural network matrix, which produces an output matrix that leads to an integration machine so that finally a classification decision result can be efficiently made. This paper’s theoretic analyses and experiments show that the MMNN can reduce the learning time and improve the generalization capability and the classification accuracy of neural networks.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
Wang LC, Der SZ, Nasrabadi NM (1998) Automatic target recognition using a feature decomposition and data-decomposition modular neural network. IEEE Trans Image Process 7(8):1113–1122
Hou Y, Du J, Wang M (2007) Neural network. Xidian University Press, Xi’an, pp 125–140
Xie W, Shi Y, Xiao P (2010) Classification of natural image based on BP neural network. Comput Eng Appl 46(2):163–166
Zhao Z, Huang D (2004) Human face recognition based on multi-features using neural networks committee. Pattern Recognit Lett 25(12):1351–1358
Oshaba AS, Ali ES, Elazim SMA (2017) PI controller design for MPPT of photovoltaic system supplying SRM via BAT search algorithm. Neural Comput Appl 4(28):651–667
Efron B, Tibshirani R (1993) An introduction to the bootstrap. Chapman and Hall, London
Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139
Shen X, Zhou Z (2000) A survey of boosting and bagging. Comput Eng Appl 36(12):31–32
Nilsson NJ (1965) Learning machines: foundations of trainable pattern-classifying systems. McGraw-Hill, New York
Ali ES, Elazim SMA, Abdelaziz AY (2016) Ant lion optimization algorithm for renewable distributed generations. Energy 11(116):445–458
Anand R, Mehrotra K, Mohan CK et al (1995) Efficient classification for multiclass problems using modular neural networks. IEEE Trans Neural Netw 6(1):117–124
Saengrung A, Abtahi A, Zilouchian A (2007) Neural network model for a commercial PEM fuel cell system. J Power Sources 172(2):749–759
Si C (2010) Learning rate parameter improve methods for BP neutral network. J Chang Normal Univ Nat Sci 29(1):26–28
Hong-mei W (2004) A neural networks multi-classifers integrated scheme based on OCON for handwritten Chinese character recognition. Comput Eng 30(16):151–152
Shuai F (2008) Research and application of the co-operative modular neural network. Wuhan University of Technology, Wuhan
Sun JX (2002) Modern pattern recognition. National University of Defense Technology Publishers, Changsha
Kittler J, Hatef M, Duin RPW, Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20:226–239
Hester T, Stone P (2013) TEXPLORE: real-time sample-efficient reinforcement learning for robots. Mach Learn 90(3):385–429
Zhang Y, Liu C (2003) A novel face recognition method based on linear discriminant analysis. J Infrared Millim Waves 22(5):327–330
Conflict of interest
The author declare that she has no conflict of interest.
About this article
Cite this article
Hu, P. A classifier of matrix modular neural network to simplify complex classification tasks. Neural Comput & Applic 32, 1367–1377 (2020). https://doi.org/10.1007/s00521-018-3631-x
- Modular neural networks
- Task decomposition
- Computational complexity
- Generalization capability