Classify Images with Conceptor Network

06/02/2015

∙

by   Yuhuang Hu, et al.

∙

0

∙

share

This article demonstrates a new conceptor network based classifier in classifying images. Mathematical descriptions and analysis are presented. Various tests are experimented using three benchmark datasets: MNIST, CIFAR-10 and CIFAR-100. The experiments displayed that conceptor network can offer superior results and flexible configurations than conventional classifiers such as Softmax Regression and Support Vector Machine (SVM).