Retinal Modeling: Segmenting Motion from Spatio-Temporal Inputs using NeuralNetworks

摘要

We applied two first-order, linear, time-varying, differential equations to thetask of segmenting motion from sequences of images. The equations are modified Grossberg formulas for long-term and short-term memory models characterizing the neurotransmitter and cell-activity levels of a synapse and neuron. We described how a two layered, sensory, neural network can be built using the equations to simulate the amacrine neurons of the retina. The model is defined using adaptive input nodes (adaptive model) and is compared to a similar model without these nodes (O and G model). By replicating the basic amacrine neuron model to form