Possible Principles Underlying the Transformations of Sensory Messages

By H. Barlow. 2012

2,030 citations recorded by the source corpus.

Subfields: Cellular and Molecular Neuroscience, Cognitive Neuroscience, Neuroscience, Cognitive Science & Psychology

How researchers see this paper

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

In Cellular and Molecular Neuroscience

In Cognitive Neuroscience

In Neuroscience

In Cognitive Science & Psychology

Citations in the corpus

View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation (2016, positive): “The class of learning rules yielding invariance includes those that emerge from principles such as sparsity and the efficient coding hypothesis [6, 7, 39].”
Representational Continuity for Unsupervised Continual Learning (2021, background): “BarlowTwins (Zbontar et al., 2021) minimizes the redundancy between the embedding vector components of the distorted versions of an instance while conserving the maximum information inspired from Barlow (1961).”
Density Modeling of Images using a Generalized Normalization Transformation (2015, background): “…a transformation so as to achieve desired statistical properties at the output is central to theories of efﬁcient sensory coding in neurobiology (Barlow, 1961; Ruderman, 1994; Rieke et al., 1995; Bell & Sejnowski, 1997; Schwartz & Simoncelli, 2001), and also lends itself naturally to the design…”
Barlow Twins: Self-Supervised Learning via Redundancy Reduction (2021, background): “In his inﬂuential article Possible Principles Underlying the Transformation of Sensory Messages (Barlow, 1961), neu-roscientist H. Barlow hypothesized that the goal of sensory processing is to recode highly redundant sensory inputs into a factorial code (a code with statistically independent…”
A Survey of Inductive Biases for Factorial Representation-Learning (2016, background): “l bias for learning [62] and provide more compact/faithful, explicit, and interpretable representations. Horace Barlow argued for the biological and computational utility of factorial representations [6, 7]. 4 1.2.1Statistical Independence When variables are statistically independent, the joint prob”
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation (2019, background): “Understanding the impact of data distributions and noise on representations has been well-studied in neuroscience [3, 42, 30].”
Life as we know it (2013, positive): “Furthermore, we have shown elsewhere [11,41] that free energy minimization is consistent with information-theoretic formulations of sensory processing and behaviour [23,42,43].”
The graphical brain: Belief propagation and active inference (2017, background): “…resolving or intrinsic (epistemic) value, variously referred to as relative entropy, mutual information, information gain, Bayesian surprise, or value of information expected under a particular policy (Barlow, 1961; Howard, 1966; Itti & Baldi, 2009; Linsker, 1990; Optican & Richmond, 1987).”
Predictive information in a sensory population (2013, background): “Another idea is that the neighboring cells in the retina should not waste their capacity by transmitting redundant signals, and minimizing this redundancy may drive the emergence of spatially differentiating receptive fields (29, 30).”
Learning to See by Moving (2015, methodology): “is organized as following: In section 2 we discuss the related work, in section 3, 4, 5 we present the method, dataset details and we conclude with the discussion in section 6. 2. Related Work Barlow [4, 3] hypothesized that good visual representations can be learnt by ﬁnding features that minimize ”
Rethinking the Representational Continuity: Towards Unsupervised Continual Learning (2021, background): “BarlowTwins (Zbontar et al., 2021) minimizes the redundancy between the embedding vector components of the distorted versions of an instance while conserving the maximum information inspired from Barlow (1961).”
Odor Discrimination in Drosophila: From Neural Population Codes to Behavior (2013, background): “, 1956; Kuffler, 1953), exerting gain control (Barlow, 1961; Olsen et al., 2010; Olsen and Wilson, 2008; Root et al., 2008), or binding neurons representing different stimulus features in synchrony (Gray et al.”