Autor:	Hu, Yuhuang, Ishwarya, M. S., Loo, Chu Kiong
Rok vydání:	2015
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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). Comment: This paper has been withdrawn by the author due to a crucial sign error in experiments
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1506.00815 Zobrazit plný text záznamu View this record from Arxiv