Unsupervised Learning by Convex and Conic Coding

Unsupervised learning algorithms based on convex and conic en(cid: 173) coders 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 encoders. The convex algorithm develops locally linear models of the input, while the conic algorithm discovers features. Both al(cid: 173) gorithms 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.

Authors

• Daniel Lee Adobe
• H. Sebastian Seung Princeton University

Keywords

No keywords are indexed for this paper.