Lattice algebra approach to single-neuron computation

Recent advances in the biophysics of computation and neurocomputing models have brought to the foreground the importance of dendritic structures in a single neuron cell. Dendritic structures are now viewed as the primary autonomous computational units capable of realizing logical operations. By changing the classic simplified model of a single neuron with a more realistic one that incorporates the dendritic processes, a novel paradigm in artificial neural networks is being established. In this work, we introduce and develop a mathematical model of dendrite computation in a morphological neuron based on lattice algebra. The computational capabilities of this enriched neuron model are demonstrated by means of several illustrative examples and by proving that any single layer morphological perceptron endowed with dendrites and their corresponding input and output synaptic processes is able to approximate any compact region in higher dimensional Euclidean space to within any desired degree of accuracy. Based on this result, we describe a training algorithm for single layer morphological perceptrons and apply it to some well-known nonlinear problems in order to exhibit its performance.

[1]  Gerhard X. Ritter,et al.  Recursion and Feedback in Image Algebra , 1991 .

[2]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[3]  Rudy Setiono,et al.  Algorithmic techniques and their applications , 1998 .

[4]  T. Poggio,et al.  Multiplying with synapses and neurons , 1992 .

[5]  Jennifer L. Davidson.  Foundation and Applications of Lattice Transforms in Image Processing , 1992 .

[6]  Peter Sussner,et al.  Morphological associative memories , 1998, IEEE Trans. Neural Networks.

[7]  Gerhard X. Ritter,et al.  Reconstruction of Patterns from Noisy Inputs Using Morphological Associative Memories , 2003, Journal of Mathematical Imaging and Vision.

[8]  Gerhard X. Ritter,et al.  Morphological perceptrons , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[9]  Paul D. Gader,et al.  Morphological shared-weight neural network for pattern classification and automatic target detection , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[10]  J. Kao,et al.  Compartmentalized and Binary Behavior of Terminal Dendrites in Hippocampal Pyramidal Neurons , 2001, Science.

[11]  Rudy Setiono,et al.  Use of a quasi-Newton method in a feedforward neural network construction algorithm , 1995, IEEE Trans. Neural Networks.

[12]  Joel L. Davis,et al.  Single neuron computation , 1992 .

[13]  Bogdan Raducanu,et al.  Morphological techniques for face localization , 2001 .

[14]  H. Heijmans.  Morphological image operators , 1994 .

[15]  G. Brindley,et al.  THE UNDERSTANDING OF THE BRAIN , 1973 .

[16]  Paul D. Gader,et al.  Continuous processing of acoustic data for land mine detection , 2002, SPIE Defense + Commercial Sensing.

[17]  Peter Sussner,et al.  Associative memories based on lattice algebra , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[18]  Rudy Setiono.  A Neural Network Construction Algorithm which Maximizes the Likelihood Function , 1995, Connect. Sci..

[19]  Paul D. Gader,et al.  Morphological shared-weight networks with applications to automatic target recognition , 1997, IEEE Trans. Neural Networks.

[20]  Peter Sussner,et al.  Observations on morphological associative memories and the kernel method , 2000, Neurocomputing.

[21]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[22]  Gordon M. Shepherd,et al.  Canonical neurons and their computational organization , 1992 .

[23]  Peter Sussner,et al.  Morphological bidirectional associative memories , 1999, Neural Networks.

[24]  Idan Segev,et al.  Methods in neuronal modeling: From synapses to networks , 1989 .

[25]  Paul D. Gader,et al.  Anti-Personnel Land Mine Detection and Discrimination Using Acoustic Data , 2002 .

[26]  Carmen Paz Suárez Araujo,et al.  Novel Neural Network Models for Computing Homothetic Invariances: An Image Algebra Notation , 2004, Journal of Mathematical Imaging and Vision.

[27]  Jennifer L. Davidson.  Simulated annealing and morphology neural networks , 1992, Optics & Photonics.

[28]  Idan Segev,et al.  Dendritic processing , 1998 .

[29]  Ning Qian,et al.  Synaptic integration by electro-diffusion in dendritic spines , 1992 .

[30]  H. Longuet-Higgins.  Understanding the Brain , 1968, Nature.

[31]  K. Lang,et al.  Learning to tell two spirals apart , 1988 .

[32]  Bartlett W. Mel.  Synaptic integration in an excitable dendritic tree. , 1993, Journal of neurophysiology.

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

[34]  H. Kunzi,et al.  Lectu re Notes in Economics and Mathematical Systems , 1975 .

[35]  Vassilios Petridis,et al.  Fuzzy lattice neural network (FLNN): a hybrid model for learning , 1998, IEEE Trans. Neural Networks.

[36]  R. Backhouse,et al.  Regular Algebra Applied to Path-finding Problems , 1975 .

[37]  William R. Holmes,et al.  Electrotonic models of neuronal dendrites and single neuron computation , 1992 .

[38]  Gerhard X. Ritter,et al.  Theory of morphological neural networks , 1990, Photonics West - Lasers and Applications in Science and Engineering.

[39]  Christof Koch,et al.  Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series) , 1998 .

[40]  Gerhard X. Ritter,et al.  Morphological neural networks and image algebra in artificial perception systems , 1992, Optics & Photonics.

[41]  B. Carré.  An Algebra for Network Routing Problems , 1971 .

[42]  R. A. Cuninghame-Green,et al.  Describing Industrial Processes with Interference and Approximating Their Steady-State Behaviour , 1962 .

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

[44]  Mark D. Plumbley,et al.  Generation and adaptation of neural networks by evolutionary techniques (GANNET) , 2005, Neural Computing & Applications.