Redundancy Reduction as a Strategy for Unsupervised Learning

By Ralph Linsker, A. Redlich. 1993

How researchers see this paper

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

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “Many UL methods are designed to maximize entropy-related, information-theoretic (Boltzmann, 1909; Kullback & Leibler, 1951; Shannon, 1948) objectives (e.g., Amari, Cichocki, & Yang, 1996; Barlowet al., 1989;Dayan&Zemel, 1995;Deco&Parra, 1997; Field, 1994; Hinton, Dayan, Frey, & Neal, 1995; Linsker, ”
Barlow Twins: Self-Supervised Learning via Redundancy Reduction (2021, background): “…and (Lindsey et al., 2020; Ocko et al., 2018; Schwartz & Simoncelli, 2001) for recent efforts), and has led to a number of algorithms for supervised and unsupervised learning (Ball´e et al., 2017; Deco & Parra, 1997; F¨oldi´ak, 1990; Linsker, 1988; Redlich, 1993a;b; Schmidhuber et al., 1996).”
Feature Extraction Through LOCOCODE (1999, unknown): “Some COCOFs explicitly favor near-factorial, minimally redundant codes of the input data (see, e.g., Watanabe, 1985; Barlow, Kaushal, & Mitchison, 1989; Linsker, 1988; Schmidhuber, 1992; Schmidhuber & Prelinger, 1993; Schraudolph & Sejnowski, 1993; Redlich, 1993; Deco & Parra, 1994).”
A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists (2017, methodology): “Unsupervised learning is thus often employed for dimensional reduction (Redlich, 1993) or feature extraction (Coates et al.”
Reconciling simplicity and likelihood principles in perceptual organization. (1996, background): “, Anderson, 1990; Fried & Holyoak, 1984; Oaksford & Chater, 1994) and those that stress the importance of finding compressed representations (Redlich, 1993; Wolff, 1982).”