A Self-Organising Neural Network for Processing Data from Multiple Sensors

TL;DR

This paper introduces a neural network model based on folded Markov chains for processing multi-sensor data, demonstrating its theoretical foundation and showing emergent ocular dominance stripes in simulations.

Contribution

It presents a novel application of folded Markov chain networks to multi-sensor data processing with detailed theoretical analysis.

Findings

Successful transformation of high-dimensional inputs into posterior probabilities

Emergence of ocular dominance stripes in simulations

Theoretical framework for multi-sensor neural processing

Abstract

This paper shows how a folded Markov chain network can be applied to the problem of processing data from multiple sensors, with an emphasis on the special case of 2 sensors. It is necessary to design the network so that it can transform a high dimensional input vector into a posterior probability, for which purpose the partitioned mixture distribution network is ideally suited. The underlying theory is presented in detail, and a simple numerical simulation is given that shows the emergence of ocular dominance stripes.