Modeling with Big Data and Machine Learning

  • ATTP Library/Seminar Room Wiedner Hauptstraße 7/2 Wien, Wien, 1040 Austria

the number of seats is limited, please drop us a line if attending (sekretariat@attp.tuwien.ac.at)

Welcome!

Abstract

Machine Learning and Big Data together offer a universal way of looking at the world phenomena, which is radically different than the classical expert based disciplinary research. However, in order to fully grasp this new potentiality, we need a new set of viewpoints, skills and technologies as a new form of literacy. We believe that this “coding literacy” will turn the classical notion of expertise from “having the answers to the known questions” to “learning to ask good questions”, where the answers can be found with an appropriate level of coding skills. 

In this talk I briefly discuss the developments of computational modeling approaches over the last decades. Further I will focus on main approaches of “object representation” and “structure of machine learning models” in an abstract level. Finally, I would like to show the results of some of our ongoing projects in different fields such as city form studies and real estate market. 

 

Vahid Moosavi, Postdoc researcher at CAAD, D-Arch, ETH Zurich

Previously trained and practiced as a systems engineer, from 2011 to 2015 I did my PhD research under the supervision of Ludger Hovestadt at the chair for Computer Aided Architectural Design (CAAD) at ETH Zurich. At the same time, from November 2011 till end of April 2015 I was involved at Future Cities Laboratory of Singapore-ETH Centre in Singapore as a researcher in simulation platform. From May 2015 I am a Post-doc researcher, based in Zurich.

In my PhD I was focused on theories of computational urban modeling and issues of “representation” and “idealization” in scientific modeling. Parallel to theoretical research, I have been always interested in applied projects in different application domains such as manufacturing systems, urban traffic dynamics, urban design, air pollution modeling, networked economy and systemic risk, natural language processing, geo-visualization, real estate analysis and recently on data driven water flow simulation.

For further information about my recent works, please visit my webpage at www.vahidmoosavi.com
For my other codes and slides on data driven modeling, please visit my GitHub Repository: https://github.com/sevamoo/data_driven_modeling