Morphological Neural Networks with Dendrite Computation: A Geometrical Approach

Abstract

Abstract. 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.

Modified Dendrite Morphological Neural Network Applied to 3D Object Recognition

“…A key issue in the design of a DMNN is its training; this is in the selection of the number of dendrites and the values of synaptic weights for each dendrite. Diverse algorithms to automatically train a DMNN can be found in [7], [8], [22], [23], [24], [25] and [26].…”