User Tools

Site Tools


people:taylor_berger:infinite_brain_paper

This is an old revision of the document!


An Indefinite Brain: Simplifying Neural Networks in a Robust Computational System

Abstract: Current models of neural networks replace the spacial features of neuronal systems in favor of a mathematical description. This paper forgoes the mathematical model in favor of a more robust, spatially distributed neural network and shows pattern recognition is not only viable, but can be reconstructed in a volatile system. We show that this type of neural network can be scaled indefinitely and learns arbitrary patterns despite adverse learning conditions that would break traditional mathematical models of neural networks.

people/taylor_berger/infinite_brain_paper.1412636415.txt.gz · Last modified: 2014/10/06 23:00 by tberge01