Dimensionality Reduction and Reconstruction using Mirroring Neural Networks and Object Recognition based on Reduced Dimension Characteristic Vector

TL;DR

This paper introduces a Mirroring Neural Network that performs non-linear dimensionality reduction, reconstructs original inputs, and classifies objects based on reduced characteristic vectors, demonstrating effective results on test patterns.

Contribution

The paper presents a novel Mirroring Neural Network architecture that simultaneously reduces dimensions, reconstructs inputs, and aids in object recognition using low-dimensional signatures.

Findings

Effective dimensionality reduction and reconstruction demonstrated

High accuracy in object classification using reduced vectors

Network architecture converges well on various test patterns

Abstract

In this paper, we present a Mirroring Neural Network architecture to perform non-linear dimensionality reduction and Object Recognition using a reduced lowdimensional characteristic vector. In addition to dimensionality reduction, the network also reconstructs (mirrors) the original high-dimensional input vector from the reduced low-dimensional data. The Mirroring Neural Network architecture has more number of processing elements (adalines) in the outer layers and the least number of elements in the central layer to form a converging-diverging shape in its configuration. Since this network is able to reconstruct the original image from the output of the innermost layer (which contains all the information about the input pattern), these outputs can be used as object signature to classify patterns. The network is trained to minimize the discrepancy between actual output and the input by back propagating the mean squared error from the output layer to the input layer. After successfully training the network, it can reduce the dimension of input vectors and mirror the patterns fed to it. The Mirroring Neural Network architecture gave very good results on various test patterns.