Computer Vision with Fast Deep Neural Nets Etc Yield Best Results on Many Visual Pattern Recognition Benchmarks
Handwriting Recognition with Fast Deep Neural Nets & LSTM Recurrent Nets (Juergen Schmidhuber)
Switzerland - best country in the world? Leading the world in science, Nobel Prizes, patents, publications, citations, quality of life, competitiveness, happiness, many sports
The formal theory of creativity by Juergen Schmidhuber explains the desire to learn motor skills, to do science, to produce art
Learning Robots Resilient machine with Continuous Self-Modeling Statistical Robotics Best robot car so far (Dickmanns, 1995) Unsupervised Learning Attentive vision STIFF - EU research project on enhancing biomorphic agility of robot arms and hands through variable stiffness & elasticity The Swiss AI Lab IDSIA What's new in Juergen Schmidhuber's page? Master's Degree in Informatics with a Major in Intelligent Systems -  a master's in computer science, with a specialization in Artificial Intelligence Home Page of Juergen Schmidhuber Juergen Schmidhuber at Singularity Summit 2009 - Compression Progress: The Algorithmic Principle Behind Curiosity and Creativity and Art and Science
The EU - a new kind of empire?
Cogbotlab Juergen Schmidhuber at TU Munich Computer Science CoTeSys: Schmidhuber's group robot population explosion Lugano, Switzerland
Click at squares above for related links

2014: Join the team that won more competitions in machine learning and pattern recognition than any other team. We are seeking an Experienced Researcher in Machine Learning for Jürgen Schmidhuber's group at the Swiss AI Lab IDSIA, for the ProtoTouch project, initially for 2 years, with possibility of prolongation. (But you will also collaborate with other lab members on other projects - we are one big family!) Funding will be provided through a prestigious Marie Curie Experienced Researcher Fellowship. Application Deadline: 20 January 2014 - see column to the right. Update of May 2014: all positions are filled!

We are looking for outstanding candidates with experience / interest in topics such as deep learning neural networks (NN), recurrent neural networks (RNN), GPU programming, evolutionary computation, RNN evolution, adaptive robotics, curiosity-driven learning & intrinsic motivations based on our theory of surprise and interestingness and the Formal Theory of Fun & Creativity, computer vision and 3D animation, reinforcement learning & policy gradients for partially observable environments, hierarchical reinforcement learning, statistical / Bayesian approaches to machine learning, statistical robotics, unsupervised learning, general artificial intelligence, universal learning machines. The general goal is to advance the state of the art in machine learning and AI.

The ProtoTouch (EU-PEOPLE) project investigates novel touch-based user interfaces (e.g., touch screens for mobile devices, touch pads for computers). In a consortium of 10 European research institutes, you will help to develop and apply machine learning methods such as deep learning neural networks to investigate the performance of novel tactile displays, and biological processes responsible for touch. (But as mentioned above, you will also collaborate with other lab members on other projects - we are one big family!) Candidates should have multidisciplinary research interests in areas like machine learning, electronic devices and neurophysiology. Candidates must not have resided or carried out their main activity in Switzerland for more than 1 year in the 3 years immediately prior to their recruitment. They also must fulfil the Experienced Researcher requirements of the Marie Curie regulations. These impose very special constraints making it difficult to find ideal candidates: Experienced Researchers must, at the time of recruitment, be in possession of a doctoral degree or have at least 4 years of full-time equivalent research experience. Experienced researchers must ALSO have less than 5 years of full-time equivalent research experience. See page 4 of the Marie Curie guidelines (PDF).

Our international project partners include neuroscientists, mathematicians, psychologists, roboticists, and other experts from the UK, Germany, Italy, Scandinavia, France, and the US.

Preferred Start: Early 2014.

Official language at IDSIA is English.

The Swiss AI Lab 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. For example, it recently won many international pattern recognition competitions. 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 magazine, the New York Times, der SPIEGEL, and many others. Numerous TV shows on Tech & Science helped to popularize IDSIA's achievements.

IDSIA is affiliated with the University of Lugano (USI) and USI's Faculty of Informatics and SUPSI. Many IDSIA alumni went on to become professors.

INSTRUCTIONS: submit your CV, a brief statement of research interests, and a list of 3 references and their email addresses to In the subject header, mention your full name followed by the keyword pro2014. For example, if your name is Jo Mo, use subject: Jo Mo pro2014. YOU MUST ALSO SUBMIT YOUR MATERIAL TO SUPSI through THIS ONLINE FORM (open from from 20 Dec 2013 - 20 Jan 2014)! (If you already applied under keyword eu2013: no need to resend; we do have your files.)

Highly competitive salaries & low Swiss taxes. There is travel funding in case of papers accepted at important conferences. (Salaries for ProtoTouch follow EU-PEOPLE rules based on years of experience.) The occupancy degree is 100%. (Here a previous similar job announcement of 2009.) Standard salaries: Postdoc CHF 72,000 / year (>US$ 81,000 / year as of 16 Dec 2013); PhD student CHF 42,000 / year (>US$ 47,000). Low taxes. There is travel funding in case of papers accepted at important conferences.

Teaching? There is an opportunity (but no need) to participate in teaching courses (in English) on robotics or machine learning, e.g., in the master's program at the University of Lugano.

Requirements are also published within the "Direttive interne SUPSI" (direttiva 7A, Art. 2) and within "Regolamento del personale SUPSI" on the website (follow SUPSI, Documenti ufficiali).

IDSIA's location: just outside the beautiful city of Lugano in Ticino (pics), the scenic southern Swiss province. Milano, Italy's center of fashion and finance, is 1 hour away, Venice 3 hours.

Switzerland is the world's leading science nation. 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. As of 2013, Switzerland is once more the world's most competitive country, according to the World Economic Forum. It also got the highest ranking in the list of happiest countries (1990s average), according to the Happiness Foundation. More.
Videos of talks by Juergen Schmidhuber
Robot Learning Artificial Curiosity Video on humanoid research with iCub baby robot in Juergen Schmidhuber's lab
Feedback Network Reinforcement Learning The RNN Book
Subgoal learning Pybrain Machine Learning Library
Evolution Evolino for time series prediction RNN-Evolution Genetic Programming SSA learns a complex task involving two agents and two keys Optimal Ordered Problem Solver Universal AI Goedel machine Theory of Beauty and Low- complexity Art Randomness and Kolmogorov complexity
Speed Prior
Computing the Universe
Click at squares above for related links