Peter Norvig on Innovation in Search and Artificial Intelligence
Posted: December 9th, 2009 | Author: Alex | Filed under: Artificial Intelligence, Search | 4 Comments »Peter Norvig gave this presentation at Citris on September 2. He emphasizes (with several recent examples), how the usage and availability of large data models and increased computing power improves problem solving approaches.
A lot of interesting subjects are covered in the presentation. Here are references to projects or papers that are mentioned:
- Seam Carving for Content-Aware Image Resizing [PDF] by Shai Avidan and Ariel Shamir presents a smarter method of image resizing. Speed of processing of modern computers greatly helped with the development of this algorithm.
- Scene Completion Using Millions of Photographs by James Hays and Alexei Efros is only possible and successful because of its large data sets.
- The More Data vs Better Algorithms slide is from Michele Banko‘s and Eric Brill‘s 2001 paper Mitigating the paucity-of-data problem: exploring the effect of training corpus size on classifier performance for natural language processing.
- Canonical image selection from the web by Shumeet Baluja, Yushi Jing and Henry Rowley compares low level features of image result matches for given queries to rank the images.
- Learning people annotation from the web via consistency learning by Jay Yagnik and Atiq Islam uses Eigenface representations and large collections of images to annotate them.
- Audiovisual Celebrity Recognition in Unconstrained Web Videos [PDF] by Mehmet Sargin, Hrishikesh Aradhye, Pedro Moreno and Ming Zhao uses both face and speech recognition to detect celebrities in videos.
- How to Write a Spelling Corrector by Peter Norvig provides spell checking in just over 20 lines of Python.
- Google made an n-gram corpus publicly available at Linguistic Data Consortium.
- Google’s Flu Trends is based on search data.
- Google Sets allows generating of sets of expressions similar to an initial set of expressions.
Also discussed: Text segmentation, statistical machine translation, MapReduce, Web bias and more.
Not only is the logic more complex in Metaphone.cc than Norvig’s spell checker, but tough for a C/C++ program to measure up to Python in terms of brevity.
The seam carving stuff was the coolest piece to me–so simple and yet so powerful.
Surprised you left out penisland.com in your summary.
Yeah – I thought his examples were beautiful. I hope those image manipulation algorithms will become standard features of image processing software in the not too distant future.
I think the section on text segmentation was largely based on/inspired by the chapter Probabilistic Language Processing from the AI book he co-wrote with Stuart Russell. I think it’s also an example of how bias within a text corpus can affect result quality.
[...] not just random » Blog Archive » Peter Norvig on Innovation in Search and Artificial Intelligence Sure to be worth a listen…Peter Norvig gave this presentation at Citris on September 2. He emphasizes (with several recent examples), how the usage and availability of large data models and increased computing power improves problem solving approaches. (tags: online video ai lectures compsci) [...]
[...] this link: not just random » Blog Archive » Peter Norvig on Innovation in Search and Artificial Intelligence 30 May 2010 | Uncategorized | Trackback | del.icio.us | Stumble it! | View Count : 0 Next Post [...]