The Library
Non-accidental properties, metric invariance, and encoding by neurons in a model of ventral stream visual object recognition
Tools
Tools
Tools
Rolls, Edmund T. and Mills, Patrick C. Mills (2018) Non-accidental properties, metric invariance, and encoding by neurons in a model of ventral stream visual object recognition. Neurobiology of Learning and Memory, 152 . pp. 20-31. doi:10.1016/j.nlm.2018.04.017
|
PDF
WRAP-non-accidental-properties-metric-invariance-encoding-neurons-Rolls-2018.pdf - Accepted Version - Requires a PDF viewer. Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0. Download (1052Kb) | Preview |
Official URL: https://doi.org/10.1016/j.nlm.2018.04.017
Abstract
When objects transform into di.erent views, some properties are maintained, such as whether the edges are convex or concave, and these non-accidental properties are likely to be important in view-invariant object recognition. The metric properties, such as the degree of curvature, may change with di.erent views, and are less likely to be useful in object recognition. It is shown that in a model of invariant visual object recognition in the ventral visual stream, VisNet, non-accidental properties are encoded much more than metric properties by neurons. Moreover, it is shown how with the temporal trace rule training in VisNet, non-accidental properties of objects become encoded by neurons, and how metric properties are treated invariantly. We also show how VisNet can generalize between di.erent objects if they have the same non-accidental property, because the metric properties are likely to overlap. VisNet is a 4-layer unsupervised model of visual object recognition trained by competitive learning that utilizes a temporal trace learning rule to implement the learning of invariance using views that occur close together in time. A second crucial property of this model of object recognition is, when neurons in the level corresponding to the inferior temporal visual cortex respond selectively to objects, whether neurons in the intermediate layers can respond to combinations of features that may be parts of two or more objects. In an investigation using the four sides of a square presented in every possible combination, it was shown that even though di.erent layer 4 neurons are tuned to encode each feature or feature combination orthogonally, neurons in the intermediate layers can respond to features or feature combinations present is several objects. This property is an important part of the way in which high capacity can be achieved in the four-layer ventral visual cortical pathway. These findings concerning non-accidental properties and the use of neurons in intermediate layers of the hierarchy help to emphasise fundamental underlying principles of the computations that may be implemented in the ventral cortical visual stream used in object recognition.
| Item Type: | Journal Article | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Subjects: | B Philosophy. Psychology. Religion > BF Psychology Q Science > QP Physiology |
||||||||
| Divisions: | Faculty of Science > Computer Science | ||||||||
| Library of Congress Subject Headings (LCSH): | Neurobiology, Memory, Visual perception | ||||||||
| Journal or Publication Title: | Neurobiology of Learning and Memory | ||||||||
| Publisher: | Academic Press | ||||||||
| ISSN: | 1074-7427 | ||||||||
| Official Date: | July 2018 | ||||||||
| Dates: |
|
||||||||
| Volume: | 152 | ||||||||
| Page Range: | pp. 20-31 | ||||||||
| DOI: | 10.1016/j.nlm.2018.04.017 | ||||||||
| Status: | Peer Reviewed | ||||||||
| Publication Status: | Published | ||||||||
| Access rights to Published version: | Restricted or Subscription Access | ||||||||
| Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
Downloads
Downloads per month over past year
