[visionlist] 10 jobs at the Swiss AI Lab IDSIA: 5 Postdocs & 5 PhD students / Theory of Surprise, Attention, Curiosity, Art, Science

[Juergen Schmidhuber]

The Robot Learning Group at the Swiss AI Lab IDSIA is expanding. We  
are seeking 5 outstanding postdocs and 5 excellent PhD students with  
experience / interest in topics such as (vision-based) adaptive  
robotics http://www.idsia.ch/~juergen/learningrobots.html , curiosity- 
driven learning & intrinsic motivations based on the theory of  
surprise and interestingness http://www.idsia.ch/~juergen/ 
interest.html , reinforcement learning & policy gradients for  
partially observable environments http://www.idsia.ch/~juergen/ 
rl.html , artificial evolution http://www.idsia.ch/~juergen/evolution.html 
  , recurrent neural networks (RNN) http://www.idsia.ch/~juergen/rnn.html 
  , RNN evolution http://www.idsia.ch/~juergen/rnnevolution.html ,  
hierarchical reinforcement learning http://www.idsia.ch/~juergen/subgoals.html 
  , statistical / Bayesian approaches to machine learning, statistical  
robotics http://www.idsia.ch/~juergen/statisticalrobotics.html ,  
unsupervised learning http://www.idsia.ch/~juergen/ica.html , general  
artificial intelligence http://www.idsia.ch/~juergen/ai.html ,  
universal learning machines http://www.idsia.ch/~juergen/unilearn.html  
& http://www.idsia.ch/~juergen/goedelmachine.html . Goal: to improve  
the state of the art in adaptive robotics and machine learning in  
general, in both theory and practice.

Funding is provided by several new EU projects, one on developmental  
robotics with adaptive iCub humanoids exploring the world like little  
infants, one on learning to control artificial hands with antagonistic  
& stiff muscles, and one on self-reference and "humanobs." But all  
postdocs and students will interact with each other and resident  
IDSIAni - we are one big family! Our international project partners  
include leading neuroscientists, machine learners, psychologists,  
roboticists, and other experts from Germany, the UK, Italy,  
Scandinavia, the US, and other countries.

Salary: commensurate with experience. Postdocs ~ SFR 72,000 / year (~  
US$ 67,000 / € 48,000 / £ 46,000 as of 1/1/09). PhD fellowships: ~ SFR  
38,000 / year (~ $ 35,000 as of 1/1/09). Low taxes! There is travel  
funding in case of papers accepted at important conferences.

Interviews: most will take place at IDSIA in Switzerland, but we will  
also arrange meetings in the period 5-17 March 2009 in the area  
Washington / New York / Boston, where JS will give the AGI-09 keynote  
and talks at various US East Coast labs.

Instructions and background: http://www.idsia.ch/~juergen/eu2009.html

Some of the jobs will be related to the theory of surprise & attention  
& exploration & curiosity (1990-2008): http://www.idsia.ch/~juergen/interest.html 
  . Recent overview:

Driven by Compression Progress: A Simple Principle Explains Essential  
Aspects of Subjective Beauty, Novelty, Surprise, Interestingness,  
Attention, Curiosity, Creativity, Art, Science, Music, Jokes (2008,  
based on keynote talk for KES 2008 and joint invited lecture for ALT  
2007 / DS 2007; variants to appear in SICE Journal & Proc. ABIALS).  
arXiv preprint: http://arXiv.org/abs/0812.4360
Abstract. I argue that data becomes temporarily interesting by itself  
to some self-improving, but computationally limited, subjective  
observer once he learns to predict or compress the data in a better  
way, thus making it subjectively simpler and more `beautiful.'  
Curiosity is the desire to create or discover more non-random, non- 
arbitrary, regular data that is novel and surprising not in the  
traditional sense of Boltzmann and Shannon but in the sense that it  
allows for compression progress because its regularity was not yet  
known. This drive maximizes interestingness, the first derivative of  
subjective beauty or compressibility, that is, the steepness of the  
learning curve. It motivates exploring infants, pure mathematicians,  
composers, artists, dancers, comedians, yourself, and recent  
artificial systems.

Juergen Schmidhuber

---

IDSIA was the smallest of the world's top ten AI labs listed in the  
1997 "X-Lab Survey" by Business Week magazine, and ranked in fourth  
place in the category "Computer Science - Biologically Inspired".  
IDSIA's most important work was done after 1997 though. It is small  
but visible, competitive, and influential. Its highly cited Ant Colony  
Optimization Algorithms broke numerous benchmark records and are now  
widely used in industry for routing, logistics etc (today entire  
conferences specialize on Artificial Ants). IDSIA is also the origin  
of the first mathematical theory of optimal Universal Artificial  
Intelligence and self-referential Universal Problem Solvers (previous  
work on general AI was dominated by heuristics). IDSIA's artificial  
Recurrent Neural Networks learn to solve numerous previous unlearnable  
sequence processing tasks through gradient descent, artificial  
evolution and other methods. Research topics also include complexity  
and generalization issues, unsupervised learning and information  
theory, forecasting, learning robots. IDSIA's results were reviewed  
not only in science journals such as Nature, Science, Scientific  
American, but also in numerous popular press articles in TIME, the NY  
Times, der SPIEGEL, etc. Many TV shows on Tech & Science helped to  
popularize IDSIA's achievements.

Switzerland is a good place for scientists. It is the origin of  
special relativity (1905) and the World Wide Web (1990), is associated  
with 105 Nobel laureates, and boasts far more Nobel prizes per capita  
than any other nation. It also has the world's highest number of  
publications per capita, the highest number of patents per capita, the  
highest citation impact factor, the most cited single-author paper,  
etc, etc. Switzerland also got the highest ranking in the list of  
happiest countries. 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://visionscience.com/pipermail/visionlist/attachments/20090130/1d570467/attachment.htm