Unsupervised Natural Experience Rapidly Alters Invariant Object Representation in Visual Cortex

By S. Gerber, Xinran Liu, I. Dulubova, Alexander C. Meyer, J. Rizo, M. Arancillo, R. Hammer, Christian Rosenmund. 2008

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

View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation (2016, positive): “There is considerable evidence from physiology and psychophysics that the brain employs a temporal-association strategy of this sort [35, 56, 12, 30, 57, 31].”
How does the brain solve visual object recognition? (2012, positive): “…and sizes can rapidly and strongly reshape the position and size tolerance of IT neurons—destroying existing tolerance and building new tolerance, depending on the provided visual experience statistics (Li and DiCarlo, 2008, 2010), and predictably modifying object perception (Cox et al., 2005).”
Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video (2015, background): “example, altering the natural temporal contiguity of visua l stimuli hinders translation invariance in the inferior tem poral cortex [27], and functions learned to preserve temporal coherence share behaviors observed in complex cells of the primary visual cortex [4].”
A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation (2009, positive): “Building upon recent findings from visual neuroscience [18,23,24], unsupervised learning could also be biased by temporal factors, such that filters that ‘‘won’’ in previous frames were biased to win again (see Supplemental Text S1 for details).”
Slowness and Sparseness Have Diverging Effects on Complex Cell Learning (2014, background): “Li & DiCarlo [39,40] found neural correlates of the learning of invariances by manipulating the statistics of the presented stimuli.”
Continual egocentric object recognition (2019, background): “This is thought to be one of the key aspects for early visual learning in children [6, 19].”
Robust Representation of Stable Object Values in the Oculomotor Basal Ganglia (2012, background): “However, most studies examined flexible value coding in which subjects were provided with a small number of options whose reward values were changed frequently (Hikosaka et al., 2006; Lau and Glimcher, 2008; Hori et al., 2009).”
Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning? (2013, methodology): “The same simulations also suggest that the theory described here is qualitatively consistent with recent results on plasticity of single IT neurons and with experimentally-induced disruptions of their invariance [54].”
A Developmental Approach to Machine Learning? (2017, background): “…extended time, the retinal information with respect to that object will necessarily and continuously change, revealing relevant transformations and the invariances for recognition that may be extendable to recognizing novel things (Földiák, 1991; Wiskott and Sejnowski, 2002; Li and DiCarlo, 2008).”
Unsupervised neural network models of the ventral visual stream (2020, background): “, the ventral pathway), computing and relaying errors back to the system as learning occurs, either rapidly in real time (68) or possibly with delayed batching as part of memory consolidation (69).”
Selectivity and tolerance (“invariance”) both increase as visual information propagates from cortical area V4 to IT (2010, background): “…the plasticity known to exist at higher stages of visual processing (Baker et al., 2002; Sigala and Logothetis, 2002; Kourtzi and DiCarlo, 2006; Li and DiCarlo, 2008), it remains an open question as to how well IT populations can encode less natural stimuli such as scrambled images after…”
Learning and disrupting invariance in visual recognition (2011, methodology): “A subsequent physiology experiment by Li and DiCarlo using a similar paradigm showed that individual neurons in primate anterior inferotemporal cortex (AIT) change their selectivity in a position-dependent manner after less than an hour of exposure to the altered visual environment [4].”
Unsupervised learning of invariant representations (2016, methodology): “The same simulations also suggest that the theory described here is qualitatively consistent with recent results on plasticity of single IT neurons and with experimentally-induced disruptions of their invariance [54].”
Semi-supervised tuning from temporal coherence (2015, background): “Thebiological plausibility of the computational learning approach here proposed is discussed in Li & DiCarlo (2008) whose authors introduce the term UTL ( Unsupervised Temporal slowness Learning ) to describe the hypothesis under which invariance is learned from temporal contiguity of object…”
Invariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet (2012, background): “Further evidence has been found to support the hypothesis (Rolls, 1992, 2008b) that unsupervised natural experience rapidly alters invariant object representation in the visual cortex (Li and DiCarlo, 2008; Li et al., 2011; cf. Folstein et al., 2010).”