A Concept Learning Approach to Multisensory Object Perception
Computer Vision and Pattern Recognition
2014-09-25 v1
Abstract
This paper presents a computational model of concept learning using Bayesian inference for a grammatically structured hypothesis space, and test the model on multisensory (visual and haptics) recognition of 3D objects. The study is performed on a set of artificially generated 3D objects known as fribbles, which are complex, multipart objects with categorical structures. The goal of this work is to develop a working multisensory representational model that integrates major themes on concepts and concepts learning from the cognitive science literature. The model combines the representational power of a probabilistic generative grammar with the inferential power of Bayesian induction.
Cite
@article{arxiv.1409.6745,
title = {A Concept Learning Approach to Multisensory Object Perception},
author = {Ifeoma Nwogu and Goker Erdogan and Ilker Yildirim and Robert Jacobs},
journal= {arXiv preprint arXiv:1409.6745},
year = {2014}
}
Comments
6 pages and 6 figures