供大家參考 Postdoc position in Learning Classifier Systems at the University of Nottingham Research Fellow Project Title: Principled Application of Learning Classifier Systems to Large-Scale Challenging Datasets (LCSxLCD) University of Nottingham - School of Computer Science Deadline for application: March 31st, 2010 Salary: 27,319 per annum Project duration: 15 months Applications are invited for the above EPSRC funded post to work on the project "Principled Application of Learning Classifier Systems to Large-Scale Challenging Datasets (LCSxLCD)". Learning Classifier Systems (LCS) are robust machine learning techniques very suitable for data mining and knowledge discovery. In recent years, there has been important research effort in advanced representations, search mechanisms, theoretical analysis, etc. The goal of this project is to study the general applicability of LCS to large-scale challenging data mining tasks. The project involves 1) the development of theoretical models for the performance of LCS when applied to large volumes of data that can inform us of when and why LCS methods are successful and also when do LCS fail and 2) proposal of new LCS methods with improved performacen and robustness based on the insight gained from these models . The person appointed will be based in the Automated Scheduling, Optimisation & Planning (ASAP) Group, which is one of four main research groups within the School of Computer Science at Nottingham. The School was ranked 8th in UK in the 2008 RAE. ASAP has been carrying out innovative research into the development and investigation of decision support, search methodologies and machine learning for a wide and diverse range of real world problem environments for the last 10 years. The group comprises 12 members of academic staff, 16 researchers, 51 PhD students and three administrators. The project also includes budget for a two-month visit for the candidate to the University of Illinois at Urbana-Champaign, USA. Candidates should have a PhD in computer science and experience in evolutionary algorithms, learning classifier systems and/or machine learning. Past experience in the development of theoretical models will be an advantage together with evidence of top quality research in the form of published papers and/or software. The successful candidate will be able to access all the resources of the rich career development programme of the University of Nottingham. Salary will be 27,319 per annum. This post is available from June 2010 and will be offered on a fixed-term contract for period of 15 months. Informal enquiries may be addressed to Dr J Bacardit, tel: 0115 846 7044, Email: [email protected]. Please note that applications sent directly to this Email address will not be accepted. To apply on-line please access: http://jobs.nottingham.ac.uk/SCI792. Please quote ref. SCI/792. Closing date: 31 March 2010. --

※ 發信站: 批踢踢實業坊(ptt.cc) ◆ From: 140.113.235.151