Throwing Down the Visual Intelligence Gauntlet

In recent years, scientific and technological advances have produced artificial systems that have matched or surpassed human capabilities in narrow domains such as face detection and optical character recognition. However, the problem of producing truly intelligent machines still remains far from be...

Full description

Bibliographic Details
Main Authors: Tan, Cheston, Leibo, Joel Z, Poggio, Tomaso
Other Authors: Tomaso Poggio
Language:en-US
Published: 2012
Subjects:
Online Access:http://hdl.handle.net/1721.1/71199
_version_ 1811078746255392768
author Tan, Cheston
Leibo, Joel Z
Poggio, Tomaso
author2 Tomaso Poggio
author_facet Tomaso Poggio
Tan, Cheston
Leibo, Joel Z
Poggio, Tomaso
author_sort Tan, Cheston
collection MIT
description In recent years, scientific and technological advances have produced artificial systems that have matched or surpassed human capabilities in narrow domains such as face detection and optical character recognition. However, the problem of producing truly intelligent machines still remains far from being solved. In this chapter, we first describe some of these recent advances, and then review one approach to moving beyond these limited successes---the neuromorphic approach of studying and reverse-engineering the networks of neurons in the human brain (specifically, the visual system). Finally, we discuss several possible future directions in the quest for visual intelligence.
first_indexed 2024-09-23T11:04:52Z
id mit-1721.1/71199
institution Massachusetts Institute of Technology
language en-US
last_indexed 2024-09-23T11:04:52Z
publishDate 2012
record_format dspace
spelling mit-1721.1/711992019-04-12T15:40:54Z Throwing Down the Visual Intelligence Gauntlet Tan, Cheston Leibo, Joel Z Poggio, Tomaso Tomaso Poggio Center for Biological and Computational Learning (CBCL) Vision Artificial intelligence In recent years, scientific and technological advances have produced artificial systems that have matched or surpassed human capabilities in narrow domains such as face detection and optical character recognition. However, the problem of producing truly intelligent machines still remains far from being solved. In this chapter, we first describe some of these recent advances, and then review one approach to moving beyond these limited successes---the neuromorphic approach of studying and reverse-engineering the networks of neurons in the human brain (specifically, the visual system). Finally, we discuss several possible future directions in the quest for visual intelligence. This research was sponsored by grants from DARPA (IPTO and DSO), National Science Foundation (NSF-0640097, NSF-0827427), AFSOR-THRL (FA8650-05-C-7262). Additional support was provided by: Adobe, Honda Research Institute USA, King Abdullah University Science and Technology grant to B. DeVore, NEC, Sony and especially by the Eugene McDermott Foundation. 2012-06-21T19:45:06Z 2012-06-21T19:45:06Z 2012 http://hdl.handle.net/1721.1/71199 Machine Learning for Computer Vision (2012); eds: Cipolla R, Battiato S, Giovanni Maria F. Springer: Studies in Computational Intelligence Vol. 411. en-US MIT-CSAIL-TR-2012-016 CBCL-309 Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported http://creativecommons.org/licenses/by-nc-nd/3.0/ 15 p. application/pdf
spellingShingle Vision
Artificial intelligence
Tan, Cheston
Leibo, Joel Z
Poggio, Tomaso
Throwing Down the Visual Intelligence Gauntlet
title Throwing Down the Visual Intelligence Gauntlet
title_full Throwing Down the Visual Intelligence Gauntlet
title_fullStr Throwing Down the Visual Intelligence Gauntlet
title_full_unstemmed Throwing Down the Visual Intelligence Gauntlet
title_short Throwing Down the Visual Intelligence Gauntlet
title_sort throwing down the visual intelligence gauntlet
topic Vision
Artificial intelligence
url http://hdl.handle.net/1721.1/71199
work_keys_str_mv AT tancheston throwingdownthevisualintelligencegauntlet
AT leibojoelz throwingdownthevisualintelligencegauntlet
AT poggiotomaso throwingdownthevisualintelligencegauntlet