Speaker: Philipp Slusallek (DFKI)
Abstract: Autonomous Driving is a large commercial but also a scientific challenge — and AI will play a central role in it. A key issue is to guarantee the correct and reliable functioning of a vehicle even in complex and critical situations in the real world. Given the ubiquitous use of Deep Learning in that context and its need for large amounts of learning data, makes this particularly challenging for critical situations, such as a kid running in front of a car. In this talk I will present and discuss our approach of using synthetic input data for learning, benchmarking, and validating of autonomous vehicles.
Speaker: Simon M. Lucas (University of Essex)
Abstract: Although AI has excelled at many narrowly defined problems, it is still very far from achieving human-like performance in terms of solving problems that it was not specifically programmed for: hence the challenge of artificial general intelligence (AGI) was developed to foster more general AI research. A promising way to address this is to pose the challenge of learning to play video games without knowing any details of the games in advance. In order to study this in a systematic way the General Video Game AI (http://gvgai.net) competition series was created. This provides an excellent challenge for computational intelligence and AI methods and initial results indicate often good though somewhat patchy performance from simulation-based methods such as Monte Carlo Tree Search and Rolling Horizon Evolutionary Algorithms. This talk will provide an overview of latest results on GVGAI, and on the use of Bayesian inferencing to boost the performance of statistical simulation-based controllers such as rolling horizon evolution.
Speaker: Francesco Bonchi (ISI Foundation)
Abstract: With the success of online social networks and microblogging platforms such as Facebook, Tumblr, and Twitter, the phenomenon of influence-driven propagation, has recently attracted the interest of computer scientists, sociologists, information technologists, and marketing specialists. In this talk we will take a data mining perspective, discussing what (and how) can be learned from a social network and a database of traces of past propagation over the social network. Starting from one of the key problems in this area, i.e. the identification of influential users, we will provide a brief overview of our recent contributions in this area. We will expose the connection between the phenomenon of information propagation and the existence of communities in social network, and we will go deeper in this new research topic arising at the overlap of information propagation analysis and community detection.