A computational exploration of complementary learning mechanisms in the primate ventral visual pathway
Autor: | Courtney J. Spoerer, Simon M. Stringer, Akihiro Eguchi |
---|---|
Rok vydání: | 2016 |
Předmět: |
Primates
Computer science Models Neurological 050105 experimental psychology 03 medical and health sciences Continuous transformation 0302 clinical medicine Animals Humans Learning 0501 psychology and cognitive sciences Computer Simulation Visual Pathways Visual Cortex Communication Spacetime business.industry 05 social sciences Cognitive neuroscience of visual object recognition Pattern recognition Invariant (physics) Sensory Systems Form Perception Ophthalmology Artificial intelligence business 030217 neurology & neurosurgery Photic Stimulation |
Zdroj: | Vision Research. 119 |
ISSN: | 0042-6989 |
Popis: | In order to develop transformation invariant representations of objects, the visual system must make use of constraints placed upon object transformation by the environment. For example, objects transform continuously from one point to another in both space and time. These two constraints have been exploited separately in order to develop translation and view invariance in a hierarchical multilayer model of the primate ventral visual pathway in the form of continuous transformation learning and temporal trace learning. We show for the first time that these two learning rules can work cooperatively in the model. Using these two learning rules together can support the development of invariance in cells and help maintain object selectivity when stimuli are presented over a large number of locations or when trained separately over a large number of viewing angles. |
Databáze: | OpenAIRE |
Externí odkaz: |