Redundancy reduction revisited

By H. Barlow. Network, 2001

693 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/633aee4e98d45d25e6ce9d1e623cffd77308f00c

How researchers see this paper

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

In Artificial Intelligence

In Cognitive Neuroscience

Citations in the corpus

Correlations and Neuronal Population Information (2016, background): “Influential work by Barlow and others has argued that an efficient representation involves, in part, minimizing correlations between encoding units (i.e., decorrelation; Barlow 2001, Simoncelli & Olshausen 2001).”
Analyzing Neural Responses to Natural Signals: Maximally Informative Dimensions (2002, background): “…ensembles which approximate those occurring in nature (Rieke et al., 1997; Simoncelli & Olshausen, 2001), and it is an attractive hypothesis that the neural representation of these natural signals may be optimized in some way (Barlow, 1961, 2001; von der Twer & Macleod, 2001; Bialek, 2002).”
Recursive ICA (2006, background): “It has long been hypothesized that the functional role of perception is to capture the statistical structure of the sensory stimuli so that appropriate action decisions can be made to maximize the chance of survival (see [10] for a brief review).”
Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams (2012, positive): “The compact relevant encodings uncovered by SFA reduce the search space for downstream goal-directed learning procedures (Schmidhuber, 1999; Barlow, 2001), especially reinforcement learning.”
Prospective Optimization (2014, background): “For example, the detection of photons at the photoreceptor is at the noise limit set by signal detection theory [14], [15] and imperfections of neuronal communication [14], [16]– [20].”
Barlow Twins: Self-Supervised Learning via Redundancy Reduction (2021, background): “This principle has been fruitful in explaining the organization of the visual system, from the retina to cortical areas (see (Barlow, 2001) for a review and (Lindsey et al., 2020; Ocko et al., 2018; Schwartz & Simoncelli, 2001) for recent efforts), and has led to a number of algorithms for…”
How Close Are We to Understanding V1? (2005, background): “Although this may be a desirable outcome in terms of redundancy reduction, we would argue that the cortex has objectives other than redundancy reduction per se (Barlow, 2001).”
Finding Neurons in a Haystack: Case Studies with Sparse Probing (2023, methodology): “In a promising demonstration of consilience, our previous discussion of superposition has striking analogues with coding theory from biological neuroscience—the study of how neurons in the brain map to sensory stimulus (Rieke et al., 1999; Olshausen & Field, 1997; Barlow, 2001).”
Underlying principles of visual shape selectivity in posterior inferotemporal cortex (2004, background): “It has been proposed that achieving a sparse representation, in which a relatively small number of neurons are active at any time, is one goal of sensory processing—sparse coding is metabolically efficient, facilitates pattern matching, and increases memory storage capacit”