Veranstaltungen im Wintersemester 2011/2012 / Künstliche Intelligenz und Maschinelles Lernen / Themen
Application of machine learning techniques in the RoboCup match: RoboCup is an international joint project to promote AI, robotics, and related fields. It is an attempt to foster artificial intelligence and robotics research by providing a standard problem where a wide range of algorithms and technologies can be integrated and examined. Machine Learning is one of the most important algorithms which includes several techniques that are applicable for a wide variety of complex tasks of Robocup. In this seminar, feasibility of applying these techniques to Robocup tasks is studied and it is shown how leveraging machine learning to RoboCup could lead to strong soccer teams.
Integrating Association Rules and Sequence Mining into MyMediaLite: Association rule mining is a standard approach in market basket analysis. The task is to
Themen
Application of machine learning techniques in the RoboCup match: RoboCup is an international joint project to promote AI, robotics, and related fields. It is an attempt to foster artificial intelligence and robotics research by providing a standard problem where a wide range of algorithms and technologies can be integrated and examined. Machine Learning is one of the most important algorithms which includes several techniques that are applicable for a wide variety of complex tasks of Robocup. In this seminar, feasibility of applying these techniques to Robocup tasks is studied and it is shown how leveraging machine learning to RoboCup could lead to strong soccer teams.
Integrating Association Rules and Sequence Mining into MyMediaLite: Association rule mining is a standard approach in market basket analysis. The task is to
- test several existing association rule and sequence mining implementations
- possibly implement one or several algorithms yourself
- integrate the most suitable implementations into the MyMediaLite recommender system library
- loading datasets
- preprocessing data
- selecting, configuring, and training of recommenders
- evaluation of recommenders
- collaborative topic models (m)
- context-aware recommendation (e.g. tags) (m)
- parallel solving of systems of equations/matrix inversion (m)