We are looking for an excellent Postdoc to work on the development of new machine learning methods for distributed streaming data generate in the context of the Internet of Things.
Learning over data generated in the context of IoT sets forth a number of challenges that have to do with the nature of the data and the processes that generate them. Most of the DM and ML algorithms assume that the data are identically independently distributed, i.e. drawn independently from stationary distributions. This is far from being the standard scenario in the IoT devices; here the data generation processes have a strong spatio-temporal dimension, which needs to be taken into account during the data modeling process if one wants to perform reliable knowledge extraction. Directly related to the spatial dimension is the issue of data fusion and aggregation, which has to be done in a manner that accommodates the spatial dimension, but also, more generally, the redundancies and interactions that exist between the different data sources, a typical scenario in a sensor network is the complementary views of the same situation that the different sensors deliver. Moreover IoT devices can regularly fail, e.g. limited battery life-time, loss of connectivity, failure, resulting in incomplete data availability. Any learning algorithm that is going to be used in such an environment for model building as well as its models should be able to cope with incomplete and missing information, in addition to coping with concept drift and changing data distributions.
The position is funded by a European H2020 research project for three years.
The successful candidate will join the data mining and machine learning team of the University of Applied Sciences, Western Switzerland, led by Prof. Alexandros Kalousis, and will also be associated with the Computer Science department of the University of Geneva within the VIPER group led by Prof. Stephane Marchand-Maillet. Our research explores a number of different issues such as: learning in high dimensional settings, dimensionality reduction and feature selection, learning with structured data (multiple kernel learning), metric and similarity learning, the exploitation of domain knowledge in the learning process. For a more detailed description the interested candidates may take a look at: http://cui.unige.ch/~kalousis/ and the list of publications within there. The greater Geneva lake area is a world-renowned education and research hub, including not only the University of Geneva, but also EPFL, and IDIAP. It offers considerable opportunities for training and exposure to data mining and machine learning, with a number of research teams being active on these and related fields. In addition the selected candidate will have ample opportunities to participate in the main ML and DM conferences.
The ideal candidate will have:
- A PhD on machine learning, data mining or other strongly related discipline.
- A very solid background in a combination of computer science and mathematics. Special areas of interest include: statistical machine learning, statistics, mathematical optimization, mathematical modelling.
- Strong publication record in the area of machine learning and data mining (e.g. ICML, NIPS, KDD, IDCM etc).
- Project experience in the area of distributed streaming data will be a considerable plus.
- Solid expertise in at least one of Matlab or R.
- Solid programming skills in scripting languages, such as perl, python, etc.
- Excellent command of English.
- Team work capacity.
Candidates should send:
- A two page CV.
- A one page motivation letter explaining why their skills, knowledge and experience make them a particularly suitable candidate for the given position.
- A 1000 words research proposal on learning over distributed streaming data.
- Their three most representative papers.
- The contact details of three referees; do not send reference letters.
Priority will be given to applications received by the 30/November/2014th, however applications will be accepted until the position is filled.
The position will be available from the 1st of January 2015 with a possibility for a later start if necessary.