Title :
Learning linear transformations
Author :
Frieze, Alan ; Jerrum, Mark ; Kannan, Ravi
Author_Institution :
Dept. of Math., Carnegie Mellon Univ., Pittsburgh, PA, USA
Abstract :
We present a polynomial time algorithm to learn (in Valiant´s PAC model) an arbitrarily oriented cube in n-space, given uniformly distributed sample points from it. In fact, we solve the more general problem of learning, in polynomial time, a linear (affine) transformation of a product distribution
Keywords :
computational complexity; learning (artificial intelligence); linear algebra; Valiant´s PAC model; arbitrarily oriented cube; distributed sample points; learning; linear transformations; polynomial time algorithm; Collaboration; Computer networks; Computer science; Gaussian distribution; Independent component analysis; Linear algebra; Mathematics; Polynomials; Probability distribution; Random variables;
Conference_Titel :
Foundations of Computer Science, 1996. Proceedings., 37th Annual Symposium on
Conference_Location :
Burlington, VT
Print_ISBN :
0-8186-7594-2
DOI :
10.1109/SFCS.1996.548495
