Title:
A Mechanism of Visual Concept Learning via Neuronal Random Projection

Thumbnail Image
Author(s)
Koplik, Peter Sebastian
Authors
Advisor(s)
Advisor(s)
Editor(s)
Associated Organization(s)
Organizational Unit
Organizational Unit
Supplementary to
Abstract
We explore the effectiveness of the random projection method, a biologically plausible, computationally efficient,and data-independentmethodofdimensionalityreductionindistinctionbetweencategoriesofvisualstimuli. We observe that a neural network tasked with approximating the original stimulus from the reduced domain generally excludes information not useful in distinguishing visual categories. This suggests that random projection may be useful in the efficient recall and recognition of visual concepts even though the projections only contain small fractions of the original information. Our findings indicate that the reconstruction of visual stimuli from the random projected domain preserves best the features most typical of that particular category of stimuli.
Sponsor
Date Issued
2018-12
Extent
Resource Type
Text
Resource Subtype
Undergraduate Thesis
Rights Statement
Rights URI