TY - GEN

T1 - Unsupervised learning by convex and conic coding

AU - Lee, D. D.

AU - Seung, Hyunjune Sebastian

PY - 1997/1/1

Y1 - 1997/1/1

N2 - Unsupervised learning algorithms based on convex and conic encoders are proposed. The encoders find the closest convex or conic combination of basis vectors to the input. The learning algorithms produce basis vectors that minimize the reconstruction error of the convex algorithm develops locally linear models of the input, while the conic algorithm discovers features. Both algorithms are used to model handwritten digits and compared with vector quantization and principal component analysis. The neural network implementations involve feedback connections that project a reconstruction back to the input layer.

AB - Unsupervised learning algorithms based on convex and conic encoders are proposed. The encoders find the closest convex or conic combination of basis vectors to the input. The learning algorithms produce basis vectors that minimize the reconstruction error of the convex algorithm develops locally linear models of the input, while the conic algorithm discovers features. Both algorithms are used to model handwritten digits and compared with vector quantization and principal component analysis. The neural network implementations involve feedback connections that project a reconstruction back to the input layer.

UR - http://www.scopus.com/inward/record.url?scp=84899021859&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899021859&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84899021859

SN - 0262100657

SN - 9780262100656

T3 - Advances in Neural Information Processing Systems

SP - 515

EP - 521

BT - Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996

PB - Neural information processing systems foundation

T2 - 10th Annual Conference on Neural Information Processing Systems, NIPS 1996

Y2 - 2 December 1996 through 5 December 1996

ER -