Pattern Recognition and Memory Mapping using Mirroring Neural Networks

TL;DR

This paper introduces Mirroring Neural Networks (MNN) for pattern recognition and associative memory, capable of unsupervised learning of image and voice data with a hierarchical, modular architecture.

Contribution

It presents a novel neural network architecture that combines pattern recognition and associative memory functions in an unsupervised, hierarchical, and modular framework.

Findings

Effective pattern recognition from sensory inputs

Unsupervised association of image and voice data

Potential for scalable, complex learning engines

Abstract

In this paper, we present a new kind of learning implementation to recognize the patterns using the concept of Mirroring Neural Network (MNN) which can extract information from distinct sensory input patterns and perform pattern recognition tasks. It is also capable of being used as an advanced associative memory wherein image data is associated with voice inputs in an unsupervised manner. Since the architecture is hierarchical and modular it has the potential of being used to devise learning engines of ever increasing complexity.