The 59th In Silico Megabank Research Seminar will be held on Friday, March 13.
This Time, we will be welcoming Dr. Shuhei Mano, The Institute of Statistical Mathematics as our lecturer, and he will be speaking on “Approximate Bayesian Computation and its Application”.

・Date: Friday, March 13, 2015
・Time: 5:00 pm-6:30 pm
・Venue: Small Conference Room 2 (3rd Floor), Tohoku Medical Megabank Building

・Title: Approximate Bayesian Computation and its Application
・Lecturer: Shuhei Mano (The Institute of Statistical Mathematics)

*This lecture is transferable as a class in the medical research-related lecture course.

・Abstract: Even though it involves numerical aspects only, Baysian data analysis is difficult to be performed with precision as it is based on complex models. Especially at the time of handling large-scale data, researchers must face the limits of computer performance.

Like the analysis of outliers, the descriptive approach is one way to analyze data as it has an advantage in the utilization the scale of data; however, there is an issue that all predictions are based on models. Approximate Bayesian Computation is a method of Baysian data analysis which allows the maximal precision within the computable domain with simulation although it does not provide clear likelihood of the models. Despite the fact that it is based on models, the structure of summary statistics is made algorithmically. Thus, the integration of data modeling and machine learning gives spice to the methodology.

In this seminar, the background, the theoretical base and method, and possible application to actual problems are introduced.

・Organizer: Yosuke Kawai, Masao Nagasaki