An Optimality Principle for Unsupervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep learning in neural networks: An overview (2014, neutral): “Many papers of the previous millennium, however, were about unsupervised learning (UL) without a teacher (e.g., Atick, Li, & Redlich, 1992; Baldi & Hornik, 1989; Barlow, Kaushal, & Mitchison, 1989; Barrow, 1987; Deco & Parra, 1997; Field, 1987; Földiák, 1990; Földiák & Young, 1995; Grossberg, 1976a,”
A Growing Neural Gas Network Learns Topologies (1994, methodology): “Linear subspaces with this property can be computed directly by principal component analysis or iteratively with a number of network models (Sanger, 1989; Oja, 1982).”
Natural image statistics and efficient coding. (1996, unknown): “Principal components calculated on 8 (cid:2) 8 image patches extracted from natural scenes using Sanger’s rule [18].”
Neural Network Approaches to Image Compression (1995, methodology): “Sanger’s generalized hebbian algorithm (GHA) [32], [33], [34] extends Oja’s model to compute the leading M principal components using the fact that the computation of any principal component is identical to that of the first with the data being modified by removing the previous principal components ”