Document Type


Publication Date

Fall 2021


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.


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

Included in

Psychology Commons



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.