Bulletin of the American Physical Society
APS April Meeting 2019
Volume 64, Number 3
Saturday–Tuesday, April 13–16, 2019; Denver, Colorado
Session E01: Poster Session I (5:45pm-7:45pm)
5:45 PM,
Saturday, April 13, 2019
Sheraton
Room: Plaza Foyer
Abstract: E01.00004 : Training Neural Networks for Object Recognition Using Blurred Images *
Presenter:
Azhar M Hussein
(University of the Virgin Islands)
Authors:
Azhar M Hussein
(University of the Virgin Islands)
Xavier Boix
(Massachusetts Institute of Technology)
Tomaso Poggio
(Massachusetts Institute of Technology)
Deep neural networks use sophisticated mathematical modeling to process data in complex ways. A shortcoming of deep neural networks is that they require a vast amount of data to train. An example of this is object recognition, a computer vision technique for identifying objects in images or videos. We hypothesized that, when training with few data examples, blurring the input images would cause the neural network to perform better compared to non-blurred images, because of the removal of unnecessary details. In this study, we trained a convolutional neural network on the blurred images, varying the amounts of blur in order to determine how the validation accuracy changes. Our preliminary results suggest that blurring the images does not help when learning from few examples; however, we cannot fully disprove the hypothesis because it requires further experimentation with other data sets and convolutional neural network models. In the future, we can use image blurring to study eccentricity dependence, a property of the human visual system that standard convolutional neural networks do not currently replicate.
*This material is based upon work supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award CCF-1231216.
Follow Us |
Engage
Become an APS Member |
My APS
Renew Membership |
Information for |
About APSThe American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics. |
© 2024 American Physical Society
| All rights reserved | Terms of Use
| Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 20740-3844
(301) 209-3200
Editorial Office
100 Motor Pkwy, Suite 110, Hauppauge, NY 11788
(631) 591-4000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 20045-2001
(202) 662-8700