Efficient training for dendrite morphological neural networks

This paper introduces an efficient training algorithm for a dendrite morphological neural network (DMNN). Given p classes of patterns, C^k, k=1, 2, ..., p, the algorithm selects the patterns of all the classes and opens a hyper-cube HC^n (with n dimensions) with a size such that all the class elements remain inside HC^n. The size of HC^n can be chosen such that the border elements remain in some of the faces of HC^n, or can be chosen for a bigger size. This last selection allows the trained DMNN to be a very efficient classification machine in the presence of noise at the moment of testing, as we will see later. In a second step, the algorithm divides the HC^n into 2^n smaller hyper-cubes and verifies if each hyper-cube encloses patterns for only one class. If this is the case, the learning process is stopped and the DMNN is designed. If at least one hyper-cube HC^n encloses patterns of more than one class, then HC^n is divided into 2^n smaller hyper-cubes. The verification process is iteratively repeated onto each smaller hyper-cube until the stopping criterion is satisfied. At this moment the DMNN is designed. The algorithm was tested for benchmark problems and compare its performance against some reported algorithms, showing its superiority.

[1]  Manuel Graña,et al.  Learning parsimonious dendritic classifiers , 2013, Neurocomputing.

[2]  Peter Sussner,et al.  An introduction to morphological associative memories in complete lattices and inf-semilattices , 2012, 2012 IEEE International Conference on Fuzzy Systems.

[3]  Gerhard X. Ritter,et al.  Grayscale image recall from imperfect inputs with a two layer dendritic lattice associative memory , 2011, 2011 Third World Congress on Nature and Biologically Inspired Computing.

[4]  Gerhard X. Ritter,et al.  Dendritic lattice associative memories for pattern classification , 2012, 2012 Fourth World Congress on Nature and Biologically Inspired Computing (NaBIC).

[5]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[6]  Gerhard X. Ritter,et al.  Lattice algebra approach to single-neuron computation , 2003, IEEE Trans. Neural Networks.

[7]  Douglas D. Dankel,et al.  A Morphological Neural Network Approach to Information Retrieval , 2007, FLAIRS Conference.

[8]  Vassilis G. Kaburlasos,et al.  Special issue: Information engineering applications based on lattices , 2011, Inf. Sci..

[9]  Bernt Schiele,et al.  Analyzing appearance and contour based methods for object categorization , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[10]  Gerhard X. Ritter,et al.  Perfect recall from noisy input patterns with a dendritic lattice associative memory , 2011, The 2011 International Joint Conference on Neural Networks.

[11]  Peter Sussner,et al.  Morphological perceptron learning , 1998, Proceedings of the 1998 IEEE International Symposium on Intelligent Control (ISIC) held jointly with IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA) Intell.

[12]  Juan Humberto Sossa Azuela,et al.  A New Associative Model with Dynamical Synapses , 2008, Neural Processing Letters.

[13]  George A. Papakostas,et al.  Lattice Computing Extension of the FAM Neural Classifier for Human Facial Expression Recognition , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Peter Sussner,et al.  Morphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm , 2011, Inf. Sci..

[15]  Gerhard X. Ritter,et al.  Morphological perceptrons with dendritic structure , 2003, The 12th IEEE International Conference on Fuzzy Systems, 2003. FUZZ '03..

[16]  Gerhard X. Ritter,et al.  Learning In Lattice Neural Networks that Employ Dendritic Computing , 2006, FUZZ-IEEE.

[17]  Ricardo de A. Araújo,et al.  Modular Morphological Neural Network Training via Adaptive Genetic Algorithm for Designing Translation Invariant Operators , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[18]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[19]  Hao Wu,et al.  Morphological neural networks for automatic target detection by simulated annealing learning algorithm , 2003, Science in China Series F: Information Sciences.

[20]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[21]  Ke-yong Wang,et al.  Image Target Detection Using Morphological Neural Network , 2009, 2009 International Conference on Computational Intelligence and Security.

[22]  Bogdan Raducanu,et al.  Morphological neural networks for vision based self-localization , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[23]  Manuel Graña.  Lattice computing and natural computing , 2009, Neurocomputing.

[24]  Juan Humberto Sossa Azuela,et al.  Morphological Neural Networks with Dendrite Computation: A Geometrical Approach , 2003, CIARP.

[25]  A. d'Anjou,et al.  Morphological Neural Networks for Localization and Mapping , 2006, 2006 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.

[26]  Manuel Graña,et al.  Optimal Hyperbox Shrinking in Dendritic Computing Applied to Alzheimer's Disease Detection in MRI , 2011, SOCO.

[27]  Peter Sussner,et al.  An introduction to morphological neural networks , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[28]  Manuel Graña,et al.  Lattice computing in hybrid intelligent systems , 2012, 2012 12th International Conference on Hybrid Intelligent Systems (HIS).

[29]  Jennifer L. Davidson,et al.  Morphology neural networks: An introduction with applications , 1993 .