The anatomy of a large-scale hypertextual Web search engine
WWW7 Proceedings of the seventh international conference on World Wide Web 7
A neural network-based intelligent metasearch engine
Information Sciences—Informatics and Computer Science: An International Journal
Item-based collaborative filtering recommendation algorithms
Proceedings of the 10th international conference on World Wide Web
Information Retrieval on the World Wide Web
IEEE Internet Computing
TextCC: new feed forward neural network for classifying documents instantly
ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
| Hi-index | 0.00 |
Feed forward neural network for classification instantly requires that the modular length of input vector is 1. On the other hand, Stereographic projection can map a point in n dimensional real space into the surface of unit sphere in (n+1) dimensional real space. Because the modular length of any point in the unit sphere of (n+1) dimensional real surface is 1 and stereographic projection is a bijective mapping, Stereographic projection can be treated as an implementation for the normalization of vector in n dimensional real space. Experimental results shown that feed forward neural network can classify data instantly and accurately if stereographic projection is used to normalized input vector for feed forward network.