The aim of the GMTaLe project is to develop a framework for analysing task-relatedness based on an approach combining graphs and non-parametric machine-learning techniques. The framework will be used for improving generalization performance of multi-task learning algorithms and the interpretability of models generated by these algorithms. The project involves one PhD student and one post-doctoral researcher. As a PhD student you will work on the following main tasks:
- reviewing state-of-the-art approaches and techniques for similarity measure design in single and multi-task learning;
- developing and comparatively analysing methods for learning-task-dependent similarity measures;
- using task-relatedness graph representation to discover task-relatedness properties and their correlation with task generalization performance;
- improving the generalization performance of existing state-of-the-art multi-task learning algorithms by means of graph-based task transformations;
- demonstrating the practical relevance of the proposed research by applying the approach to real-life case studies.
Requirements
You should meet the following requirements:
- a Master's degree (or equivalent) in Computer Science, Mathematics or a related field, with a strong interest in machine learning and graph theory;
- commitment and a cooperative attitude;
- excellent proficiency in written and spoken English.
Organization
Radboud University Nijmegen is one of the leading academic communities in the Netherlands. Renowned for its green leafy campus, modern buildings, and state-of-the-art equipment, it has nine faculties and more than 17,500 students enrolled in approximately 90 study programmes. The university is situated in the oldest Dutch city, close to the German border, on the banks of the river Waal. The city has a rich history and one of the liveliest city centres in the Netherlands.
The machine-learning group of the Intelligent Systems Section of the Institute for Computing and Information Sciences (iCIS) at Radboud University Nijmegen conducts research in machine learning and artificial intelligence in general, with applications to neuroscience, bioinformatics, and other fields.
Website: www.ru.nl/is/ml
Conditions of employment
Employment: 1,0 fte
Maximum salary per month, based on a fulltime employment: € 2,612 gross/month
The starting salary is €2,042 per month and will increase to €2,612 per month in the fourth year. PhD scale.
Additional conditions of employment
You will be appointed as a PhD student for a period of four years. Your performance will be evaluated after 18 months. If the evaluation is positive, the contract will be extended by 2.5 years.
Additional Information
Dr. Elena Marchiori
Telephone: +31 24 36 52647
E-mail: elenam@cs.ru.nl
Application
You can apply for the job (mention the vacancy number 62.07.10) before 30 April 2010 by sending your application -preferably by email- to:
RU Nijmegen, FNWI, P&O, mrs. D. Reinders
P.O. Box 9010, 6500 GL Nijmegen, NL
Telephone: +31 24 3652027
E-mail: pz@science.ru.nl
- reviewing state-of-the-art approaches and techniques for similarity measure design in single and multi-task learning;
- developing and comparatively analysing methods for learning-task-dependent similarity measures;
- using task-relatedness graph representation to discover task-relatedness properties and their correlation with task generalization performance;
- improving the generalization performance of existing state-of-the-art multi-task learning algorithms by means of graph-based task transformations;
- demonstrating the practical relevance of the proposed research by applying the approach to real-life case studies.
Requirements
You should meet the following requirements:
- a Master's degree (or equivalent) in Computer Science, Mathematics or a related field, with a strong interest in machine learning and graph theory;
- commitment and a cooperative attitude;
- excellent proficiency in written and spoken English.
Organization
Radboud University Nijmegen is one of the leading academic communities in the Netherlands. Renowned for its green leafy campus, modern buildings, and state-of-the-art equipment, it has nine faculties and more than 17,500 students enrolled in approximately 90 study programmes. The university is situated in the oldest Dutch city, close to the German border, on the banks of the river Waal. The city has a rich history and one of the liveliest city centres in the Netherlands.
The machine-learning group of the Intelligent Systems Section of the Institute for Computing and Information Sciences (iCIS) at Radboud University Nijmegen conducts research in machine learning and artificial intelligence in general, with applications to neuroscience, bioinformatics, and other fields.
Website: www.ru.nl/is/ml
Conditions of employment
Employment: 1,0 fte
Maximum salary per month, based on a fulltime employment: € 2,612 gross/month
The starting salary is €2,042 per month and will increase to €2,612 per month in the fourth year. PhD scale.
Additional conditions of employment
You will be appointed as a PhD student for a period of four years. Your performance will be evaluated after 18 months. If the evaluation is positive, the contract will be extended by 2.5 years.
Additional Information
Dr. Elena Marchiori
Telephone: +31 24 36 52647
E-mail: elenam@cs.ru.nl
Application
You can apply for the job (mention the vacancy number 62.07.10) before 30 April 2010 by sending your application -preferably by email- to:
RU Nijmegen, FNWI, P&O, mrs. D. Reinders
P.O. Box 9010, 6500 GL Nijmegen, NL
Telephone: +31 24 3652027
E-mail: pz@science.ru.nl
