Morphological Neural Networks with Dendrite Computation: A Geometrical Approach
Part of the
Lecture Notes in Computer Science
book series (LNCS, volume 2905)
Morphological neural networks consider that the information entering a neuron is affected additively by a conductivity factor called synaptic weight. They also suppose that the input channels account with a saturation level mathematically modeled by a MAX or MIN operator. This, from a physiological point of view, appears closer to reality than the classical neural model, where the synaptic weight interacts with the input signal by means of a product; the input channel forms an average of the input signals. In this work we introduce some geometrical aspects of dendrite processing that easily allow visualizing the classification regions, providing also an intuitive perspective of the production and training of the net.
KeywordsInput Signal Output Neuron Synaptic Weight Input Neuron Input Channel
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
to read the full conference paper text
Hudson, D.L.: Neural Networks and Artificial Intelligence for Biomedical Engineering. IEEE Press, Los Alamitos (2000)Google Scholar
Ritter, G.X., Wilson, J.N.: Computer Vision Algorithms in Image Algebra. CRC, Boca Raton (2001)zbMATHGoogle Scholar
Martínez, J.: Ordered Algebraic Structures. Kluwer Academic, Dordrecht (2002)zbMATHGoogle Scholar
Ritter, G.X., Urcid, G.: Lattice Algebra Approach to Single Neuron Computation. IEEE Transactions on Neural Networks (May 2003)Google Scholar
© Springer-Verlag Berlin Heidelberg 2003