Classify Images with Conceptor Network
Yuhuang Hu, M. S. Ishwarya, Chu Kiong Loo · arXiv (Cornell University) · 2015
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).