home KERMIT
Research Unit Knowledge-based Systems
N2N ugent
sitemap
Home
 
 
PhD vacancies
Fully funded PhD studentship in constructive machine learning for the life sciences at Ghent University

Duration of studentship: 4 years
Studentship start date: September 2015

Application closing date: July 1st (will be extended if no suitable candidate is found). Apply as soon as possible to avoid disappointment!

Project description:

Constructive machine learning describes a class of related machine learning problems where the ultimate goal of learning is not to find a good model of the data but instead to find one or more particular instances of the domain which are likely to exhibit desired properties. While traditional approaches choose these domain instances from a given set/databases of unlabeled domain instances, constructive machine learning is typically iterative and searches an infinite or exponentially large instance space. Interesting applications in the life sciences are in the domains of chemistry (e.g. de novo drug design), biology (e.g. gene design, metabolic path design, RNA polymer design), food sciences (e.g. generation of novel food recipes or cocktails) and spatio-temporal modelling (e.g. prediction of spatio-temporal maps that evolve in time, as in climate analysis and ecology). This project will focus on the development of novel constructive machine learning methods with a particular emphasis on large output spaces, streaming data and decomposition techniques for output spaces.

Background information:

The studentship is available in the research unit KERMIT of Ghent University (acronym for Knowledge Extraction and Representation Management by means of Intelligent techniques) under supervision of Prof. Willem Waegeman. KERMIT is a young interdisciplinary team of mathematicians, engineers and computer scientists, and it draws upon intelligent techniques resulting from the cross-fertilization between the fields of computational intelligence and operations research. The main focus is on mathematical and computational aspects of relational structures as knowledge instruments, with emphasis on the fields of fuzzy set theory and machine learning. KERMIT serves as an attraction pole for applications in the applied biological sciences, and serves colleagues in hydrology, ecology, bacterial taxonomy, genome analysis, integrated water management, geographical information systems, forest management, metabolic engineering, soil science, bioinformatics, systems biology, etc.

The ideal candidate for the position has the following profile:

    - An MSc degree in (Bio-)Engineering, Computer Science, Mathematics, Statistics, Bio-informatics, Physics, or equivalent Ė candidates from outside Belgium are welcome.
    - An interest in fundamental machine learning research, as well as practical applications in the life sciences
    - In-depth experience with at least one programming language (Matlab, R, Python, Java, etc.)
    - An interest for applied mathematics, data management and data analysis in general
    - Good knowledge of machine learning and statistical methods is a strong asset
    - Fluent in English (speaking and writing, as demonstrated by personal texts)
    - Knowledge of Dutch is an asset, but not a must
    - Team player with good communication skills


How to apply:

Send your c.v., a motivation letter and a copy of your MSc.-thesis and/or any relevant publications to Mrs. Ruth Van Den Driessche (ruth.vandendriessche@ugent.be).

------------

Full-time junior assistant (PhD student) in Applied Mathematics, Ghent University Ė Ghent University Global Campus, Korea

Last application date: June 7, 2015.
Department: BW011 - Dept. of Mathematical Modelling, Statistics and Bioinformatics.
Contract: Limited duration.
Degree: Master degree in one of the following: mathematics, systems and control, bioscience engineering, chemistry or chemical engineering.
Occupancy rate: 100%.
Vacancy type: Academic Assisting Staff.

Starting date: August 15, 2015.

--

Ghent University Global Campus, Korea (GUGC-K) is the first campus of Ghent University outside Belgium. This brand new campus is situated in Incheon, South-Korea. GUGC-K integrates educational and research facilities in a single building. Ghent University has the ambition to organize a first-rate, truly European education in Asia and to develop excellent research in the fields of Molecular biotechnology, Environmental and Food technology

While the candidate will mainly work under the supervision of Prof. Shodhan Rao located at the campus in Korea, he/she will be co-supervised by Prof. Bernard de Baets located in Ghent. The candidate will therefore have the opportunity to spend at least one month every summer at the campus in Ghent during the course of his/her PhD. The terms of employment at GUGC-K are comparable to those at the campus in Ghent. However free student accommodation and a yearly travel budget are foreseen.

Profile of the candidate

    - hold or expect to hold by August 2015 a Master of Science in one of the following disciplines: mathematics, systems and control, bioscience engineering, chemistry, chemical engineering. Exceptional candidates from other science/engineering backgrounds will also be considered.
    - should have had a rigorous undergraduate mathematics training and in general a strong background in mathematics.
    - be highly motivated to conduct research in the area of applied mathematics, specifically in mathematical biology/chemistry.
    - should have an excellent academic track record.
    - knowledge of biology or chemistry at undergraduate level is preferable although not mandatory.

Job description

    - to conduct research in the area of mathematical/systems biology particularly in the area of discretization of reaction-diffusion biochemical networks.
    - to assist his/her supervisor in teaching undergraduate mathematics courses at Ghent University Global Campus, Korea.
--

Applications should be sent no later than June 7th , 2015 by email to shodhan.rao@ghent.ac.kr with the application letter, the required transcripts (copies of degrees) and an overview of the study results attached (please merge all the documents in one file). The candidate will receive an e-mail confirming receipt of the application.
 last updated Fri 15 May 2015 00:00:00  
International Workshop on Big Multi-Target Prediction
We are organizing the first international workshop on ďBig Multi-target predictionĒ at the 2015 European Conference on Machine Learning in Porto, Portugal, September 11th. The workshop is a follow-up of a tutorial that we organized at ICML 2013 and a workshop at ECML/PKDD 2014. All info about the workshop can be found at:

http://www.kermit.ugent.be/big-multi-target-prediction/
 last updated Wed 22 Apr 2015 00:00:00  
2015 IEEE CIS Outstanding TFS Paper Award
The long-standing cooperation between members of KERMIT and members of the Department of Information Technology and the Turku Centre for Computer Science (University of Turku, Finland) has resulted in the 2015 IEEE Computational Intelligence Society Outstanding TFS Paper Award for their contribution "A kernel-based framework for learning graded relations from data" (W. Waegeman, T. Pahikkala, A. Airola, T. Salakoski, M. Stock and B. De Baets) which has appeared in the December 2012 issue of IEEE Transactions on Fuzzy Systems.

More information
 last updated Mon 18 Aug 2014 00:00:00  
Interdisciplinary Doctoral Studies in Mathematical Modeling at the University of Gdansk: Recruitment Started
The new Interdisciplinary Doctoral Studies in Mathematical Modelling initiated by the Faculty of Mathematics, Physics and Informatics of the University of Gdansk offer a unique chance to work on the topics where mathematics meets other sciences (like biology, physics, chemistry, etc.). Here you can test how abstract ideas may be applied to model real-life problems. The model of the studies is developed in cooperation with the KERMIT research unit at Ghent University (Belgium) sharing its huge scientific experience in applied mathematics. The studies offer 10 different topics to choose from that are supposed to turn into 10 PhD theses promoted by the specialists in applied mathematics. Studies are realized in their entirety in the English language. In the academic year 2014-15 the studies will be supported by the NCBiR grant allowing our students to focus on the science and build their own scientific contacts.

More information

Recruitment (10 PhD positions) for the academic year 2014-2015 is open

Poster (PDF)
 last updated Thu 3 Jul 2014 00:00:00  
PhD position: The influence of behavior on the aggregated exposure to chemicals
KERMIT, in collaboration with VITO, is looking for a PhD candidate to do research on "The influence of behavior on the aggregated exposure to chemicals". Start date: as soon as possible. More information (PDF). Email us for an English version.
 last updated Wed 20 Mar 2013 00:00:00  
Five most recent KERMIT publications in Web of Science
(362) G. Gonnelli, M. Stock, J. Verwaeren, D. Maddelein, B. De Baets, L. Martens and S. Degroeve, A decoy-free approach to the identification of peptides, Journal of Proteome Research 14 (2015), 1792-1798.

(361) J. Verwaeren, P. Van der WeeŽn and B. De Baets, A search grid for parameter optimization as a byproduct of model sensitivity analysis, Applied Mathematics and Computation 261 (2015), 8-27.

(360) J. Verwaeren, M. Rademaker and B. De Baets, An interval estimator for the unmixing of mixtures with set-based source descriptions, Internat. J. Approximate Reasoning 60 (2015), 71-92.

(359) B. De Baets, H. De Meyer, J. KalickŠ and R. Mesiar, On the relationship between modular functions and copulas, Fuzzy Sets and Systems 268 (2015), 110-126.

(358) S. Muzzioli, A. Ruggieri and B. De Baets, A comparison of fuzzy regression methods for the estimation of the implied volatility smile function, Fuzzy Sets and Systems 266 (2015), 131-143.

 last updated Mon 20 Apr 2015 00:00:00  
Doctoral Degree for Damiano Oldoni
On January 12, 2015, Damiano Oldoni successfully defended his Ph.D. thesis "Computational modelling for soundscape analysis inspired by human auditory perception and its application in monitoring networks" and was awarded the title of Doctor of Engineering Physics.
 last updated Mon 12 Jan 2015 00:00:00  
Doctoral degree for MichaŽl Vyverman
On December 5, 2014, MichaŽl Vyverman successfully defended his Ph.D. thesis "ALFALFA: fast and accurate mapping of long next generation sequencing reads" and was awarded the title of Doctor of Computer Science.
 last updated Fri 5 Dec 2014 00:00:00  
Doctoral degree for Seyed Hossein Chavoshi
On December 1, 2014, Seyed Hossein Chavoshi successfully defended his Ph.D. thesis "New directions in the analysis of movement patterns in space and time" and was awarded the title of Doctor of Science: Geomatics and Surveying.
 last updated Mon 1 Dec 2014 00:00:00  
Doctoral degree for Pieter Van der WeeŽn
On September 10, 2014, Pieter Van der WeeŽn successfully defended his Ph.D. thesis "Meso-scale modelling of reaction-diffusion processes using cellular automata" and was awarded the title of Doctor of Applied Biological Sciences.
 last updated Wed 10 Sep 2014 00:00:00  
Doctoral degree for Tarad Jwaid
On September 8, 2014, Tarad Jwaid successfully defended his Ph.D. thesis "Semi-linear and semi-quadratic conjunctive aggregation functions" and was awarded the title of Doctor of Mathematics.
 last updated Mon 8 Sep 2014 00:00:00  
Doctoral degree for Davide Martinetti
On July 24, 2014, Davide Martinetti successfully defended his Ph.D. thesis "Fuzzy and probabilistic approaches to individual choice and preference: rationality conditions and their relationships" and was awarded the title of Doctor of Mathematics and Statistics of the University of Oviedo, Spain.
 last updated Thu 24 Jul 2014 00:00:00  
Doctoral degree for Jan Verwaeren
On June 23, 2014, Jan Verwaeren successfully defended his Ph.D. thesis "Mathematical optimization methods for the analysis of compositional data: subset selection, unmixing and prediction" and was awarded the title of Doctor of Applied Biological Sciences.
 last updated Mon 23 Jun 2014 00:00:00  
Former post-doc Willem Waegeman appointed Professor
On Oct 1, 2013, Willem Waegeman joined the Department of Mathematical Modelling, Statistics and Bioinformatics as a lecturer in applied mathematics, specialized in machine learning. This way, KERMIT is finally home to a second professor. Willem will further expand the activities in our predictive modelling research line. Good luck!
 last updated Tue 1 Oct 2013 00:00:00  
Nomination for Best Student Paper Award for Tarad Jwaid

Best Student Paper Award Tarad Jwaid was nominated for the Best Student Paper Award for his contribution "Biconic semi-copulas with a given section" (T. Jwaid, B. De Baets, H. De Meyer and R. Mesiar) at the Eighth Conference of the European Society for Fuzzy Logic and Technology (Milano, Italy, Sep 2013).

More information (PDF)
 last updated Mon 16 Sep 2013 00:00:00  
Second Prize in Student Awards for Pieter Van der WeeŽn
The Second Prize in the Student Awards in the Contributed Session Category was awarded for the contribution "A discrete stochastic model for pitting corrosion" (P. Van der WeeŽen, A.M. Zimer, E.C. Pereira, O.M. Bruno and B. De Baets) at the Internat. Conference on Applied Mathematics, Modeling and Computational Science (Waterloo, Ontario, Canada, Aug 2013).

http://www.ammcs2013.wlu.ca/ammcs2013-awards.html
 last updated Mon 16 Sep 2013 00:00:00  
Best Paper Award for Tarad Jwaid
The Best Paper Award was awarded for the contribution "On the construction of semiquadratic copulas" (T. Jwaid, B. De Baets and H. De Meyer) at the Seventh Internat. Summer School on Aggregation Operators (Pamplona, Spain, July 2013).

More information (PDF)
 last updated Tue 30 Jul 2013 00:00:00  
Doctoral Degree for Jasper Van doninck
On April 16, 2013, Jasper Van doninck successfully defended his Ph.D. thesis "Remotely sensed soil moisture proxies with application to modelling the spatial distribution of C. imicola" and was awarded the title of Doctor of Applied Biological Sciences.
 last updated Tue 16 Apr 2013 00:00:00  
Doctoral Degree for Muhammad Zaini Ahmad
On Dec 17, 2012, Muhammad Zaini Ahmad successfully defended his Ph.D. thesis "Numerical method for computing fuzzy-valued functions and its applications to differential equations" and was awarded the title of Doctor of Industrial Computing at the National University of Malaysia.
 last updated Mon 8 Apr 2013 00:00:00  
Mission Statement
KERMIT (acronym for Knowledge Extraction, Representation and Management by means of Intelligent Techniques) is a young interdisciplinary team of mathematicians, engineers and computer scientists initiated by Bernard De Baets in 2000. KERMIT is a partner of the iKnow consortium.

KERMIT draws upon intelligent techniques resulting from the cross-fertilization between the fields of computational intelligence and operations research. The main focus is on mathematical and computational aspects of relational structures as knowledge instruments, with emphasis on the fields of fuzzy set theory and machine learning. Particular attention goes to the modelling of imprecision and uncertainty.

KERMIT serves as an attraction pole for applications in the applied biological sciences, and serves colleagues in hydrology, ecology, bacterial taxonomy, genome analysis, integrated water management, geographical information systems, forest management, metabolic engineering, soil science, bioinformatics, plant systems biology, etc.
 last updated Wed 14 Mar 2007 14:00:00