Connectionists: Two PhD positions in deep machine learning (Idiap, Switzerland, affiliated to EPFL)

[Francois Fleuret]

The Idiap Research Institute, affiliated with École Polytechnique Fédérale de Lausanne, seeks two PhD students in machine learning to develop new techniques to speed up the training of deep architectures using importance sampling, and to learn automatically network architectures from data. The starting date is early 2017.

  http://www.idiap.ch/~fleuret/hiring.html

These positions are funded by the Swiss National Science Foundation, and the candidates will be doctoral students at EPFL. Research will be conducted in the Computer Vision and Learning group at the Idiap research institute, under the supervision of Dr. François Fleuret.

* Summary

Large neural networks demonstrate excellent performance for applications such as image classification, object detection, speech processing, and natural language processing. They are currently the standard machine-learning tool to deal with such problems when large training sets are available.

Two key issues remain. The first is the computational effort during training which is often the limiting factor in practice. The second is the need for a careful design of the architecture, for which very few heuristics exist. The two lines of research we will pursue aim at addressing the first through the development of novel importance-sampling strategies that focus the computational effort over the samples which influence the parameter optimization the most. The second point will be addressed by revisiting variants of the Boosting algorithm in the context of deep architectures.

This work will mix theoretical developments in machine learning with the implementation and benchmarking of algorithms on real-world data.

Applicants must imperatively be self-sufficient programmers and have a strong background in mathematics. They should be familiar with several of the following topics: probabilities, applied statistics, information theory, signal processing, optimization, algorithmic, and development with some of the modern "deep learning" frameworks (e.g. Torch, Theano, TensorFlow)

Please contact francois.fleuret at idiap.ch for additional information.

* About Idiap

Idiap is an independent, non-profit research institute recognized and supported by the Swiss Government, and affiliated with the Ecole Polytechnique Fédérale de Lausanne (EPFL). It is located in the town of Martigny in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. It is within close proximity to Geneva and Lausanne. Although Idiap is located in the French part of Switzerland, English is the working language. Free French lessons are provided.

Idiap offers competitive salaries and conditions at all levels in a young, dynamic, and multicultural environment. Idiap is an equal opportunity employer and is actively involved in the "Advancement of Women in Science" European initiative. The Institute seeks to maintain a principle of open competition (on the basis of merit) to appoint the best candidate, provides equal opportunity for all candidates, and equally encourage both genders to apply.

-- 
Francois Fleuret                         http://www.idiap.ch/~fleuret/