Difference between revisions of "DT's Kahn Presentation 4/21/16"
(→Reconstructing the World in Six Days) |
(→Mike Tyka, The Art of Neural Networks) |
||
(11 intermediate revisions by the same user not shown) | |||
Line 2: | Line 2: | ||
---- | ---- | ||
+ | <br /> | ||
+ | {| | ||
+ | | | ||
+ | __TOC__ | ||
+ | | | ||
+ | <bluebox> | ||
+ | This page contains links to 3 videos that you might want to watch before my presentation on 4/21/16. The paper listed at the end provides background material and is not required. | ||
+ | </bluebox> | ||
+ | |} | ||
+ | <br /> | ||
<br /> | <br /> | ||
=Videos= | =Videos= | ||
Line 7: | Line 17: | ||
==Zittrain on Wikipedia== | ==Zittrain on Wikipedia== | ||
<br /> | <br /> | ||
− | * [http://bigthink.com/videos/the-model-for-wikipedia-is-truly-unique Jonathan Zittrain on Wikipedia] (3 minutes) | + | * [http://bigthink.com/videos/the-model-for-wikipedia-is-truly-unique Jonathan Zittrain on Wikipedia] (3 minutes). Zittrain is the George Bemis Professor of International Law, Harvard Law School, Harvard Kennedy School of Government, and Professor of Computer Science, Harvard School of Engineering and Applied Sciences. He is also the co-founder, Director, and Faculty Chair of the Berkman Center for Internet & Society. |
<br /> | <br /> | ||
[[Image:Zittrain.png|center|500px]] | [[Image:Zittrain.png|center|500px]] | ||
<br> | <br> | ||
+ | |||
==Reconstructing the World in Six Days== | ==Reconstructing the World in Six Days== | ||
<br /> | <br /> | ||
− | Researchers at the University of North Carolina have processed 100 million images from Yahoo and used the geolocation information of the camera, along with the image, to recreate a 3D model of various buildings. Once | + | Researchers at the University of North Carolina have processed 100 million images from Yahoo and used the geolocation information of the camera, along with the image, to recreate a 3D model of various buildings depicted in the photographs. Once a 3D object is reconstructed, computer software can be used to "move" around the object. The video shows such reconstructions. 8 min 30 sec. |
<br /> | <br /> | ||
<center><videoflash>bRYqyoqUJuM</videoflash></center> | <center><videoflash>bRYqyoqUJuM</videoflash></center> | ||
Line 23: | Line 34: | ||
* '''Data Set''': The 100 million image dataset used in this paper was obtained from Yahoo: One Hundred Million Creative Commons Flickr Images For Research, Yahoo Flickr Creative Commons 100M | * '''Data Set''': The 100 million image dataset used in this paper was obtained from Yahoo: One Hundred Million Creative Commons Flickr Images For Research, Yahoo Flickr Creative Commons 100M | ||
<br /> | <br /> | ||
+ | |||
==Mike Tyka, The Art of Neural Networks== | ==Mike Tyka, The Art of Neural Networks== | ||
<br /> | <br /> | ||
− | (With thanks to MJ Wraga for discovering this video)<br /> | + | (With thanks to MJ Wraga for discovering this video.)<br /> |
− | From the YouTube page: "Mike Tyka, who is both artist and computer scientist, talks about the power of neural networks. These algorithms are capable to transform computers into artists that can generate breathtaking paintings, music and even poetry." | + | * From the YouTube page: "Mike Tyka, who is both artist and computer scientist, talks about the power of neural networks. These algorithms are capable to transform computers into artists that can generate breathtaking paintings, music and even poetry." |
+ | * The tool used by Mike Tyka in the video is [http://deepdreamgenerator.com/ Deep Dream], created and released to the public (the source code is available) by Google. | ||
+ | * 16 minutes. | ||
+ | <br /> | ||
<br /> | <br /> | ||
<center><videoflash>0qVOUD76JOg</videoflash></center> | <center><videoflash>0qVOUD76JOg</videoflash></center> | ||
Line 32: | Line 47: | ||
* [[Image:weirdThingDeepDream.png|center|500px|link=http://i.imgur.com/5NlWLKg.gifv]] | * [[Image:weirdThingDeepDream.png|center|500px|link=http://i.imgur.com/5NlWLKg.gifv]] | ||
<br /> | <br /> | ||
+ | |||
+ | =Non Required Reading= | ||
+ | <br /> | ||
+ | If you are so inclined and have time, you may find this article of interest: | ||
+ | <br /> | ||
+ | * [http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=4305569&url=http%3A%2F%2Fieeexplore.ieee.org%2Fstamp%2Fstamp.jsp%3Ftp%3D%26arnumber%3D4305569 Hepp, M., K. Siorpaes, D. Bachlechner, Harvesting Wiki Consensus: Using Wikipedia Entries as Vocabulary for Knowledge Management], IEEE Internet Computing, Vol. 11, No. 5, Sept-Oct 2007, pp. 54-65. | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | <br /> | ||
+ | [[Category:Kahn Institute]] |
Latest revision as of 16:43, 17 April 2016
--D. Thiebaut (talk) 13:37, 17 April 2016 (EDT)
This page contains links to 3 videos that you might want to watch before my presentation on 4/21/16. The paper listed at the end provides background material and is not required. |
Videos
Zittrain on Wikipedia
- Jonathan Zittrain on Wikipedia (3 minutes). Zittrain is the George Bemis Professor of International Law, Harvard Law School, Harvard Kennedy School of Government, and Professor of Computer Science, Harvard School of Engineering and Applied Sciences. He is also the co-founder, Director, and Faculty Chair of the Berkman Center for Internet & Society.
Reconstructing the World in Six Days
Researchers at the University of North Carolina have processed 100 million images from Yahoo and used the geolocation information of the camera, along with the image, to recreate a 3D model of various buildings depicted in the photographs. Once a 3D object is reconstructed, computer software can be used to "move" around the object. The video shows such reconstructions. 8 min 30 sec.
- Reconstructing the World* in Six Days *(As Captured by the Yahoo 100M Image Dataset) (CVPR 2015),
- Authors: Jared Heinly, Johannes L. Schönberger, Enrique Dunn, Jan-Michael Frahm
- Presented at the Computer Vision and Pattern Recognition conference (CVPR), 2015
- Web site: http://cs.unc.edu/~jheinly/reconstructing_the_world.html
- Data Set: The 100 million image dataset used in this paper was obtained from Yahoo: One Hundred Million Creative Commons Flickr Images For Research, Yahoo Flickr Creative Commons 100M
Mike Tyka, The Art of Neural Networks
(With thanks to MJ Wraga for discovering this video.)
- From the YouTube page: "Mike Tyka, who is both artist and computer scientist, talks about the power of neural networks. These algorithms are capable to transform computers into artists that can generate breathtaking paintings, music and even poetry."
- The tool used by Mike Tyka in the video is Deep Dream, created and released to the public (the source code is available) by Google.
- 16 minutes.
Non Required Reading
If you are so inclined and have time, you may find this article of interest:
- Hepp, M., K. Siorpaes, D. Bachlechner, Harvesting Wiki Consensus: Using Wikipedia Entries as Vocabulary for Knowledge Management, IEEE Internet Computing, Vol. 11, No. 5, Sept-Oct 2007, pp. 54-65.