Document Type

Poster

Publication Date

Summer 2021

Abstract

The form of visual feature learning called segmentation involves learning components from whole objects, whereas unitization is learning whole objects via repeated exposure to the key parts. While some computer vision approaches get similar results as empirical findings from humans, the models are not very biologically plausible. This project presents a web-accessible version of a neural network model of flexible visual feature learning developed by Roberts and Goldstone. Here we use HTML and javascript to create a website which allows users to draw and train with their own input patterns, adjust parameters, and then test the features learned by the network.

Comments

Funding: J. William and Katherine C. Asher Endowed Research Fund

Included in

Psychology Commons

Share

COinS