We are meeting again at Liip as we did in the first meetup and it will be nice as it is a first rate location and we'll be able to stick around for drinks and nibbles.
• 🌩 Lightning talks! Talk for 5minutes on a topic of your choice. Still need more: Don't be shy! All skill-levels are welcome.
• Explainable AI: How can you explain the decision made by a black box machine learning algorithm? by Christoph Molnar
Please follow the link and submit proposals of lighting talks of your own, somebody that you would like to hear from, or topics that can be treated in a short duration
• Coding as Literacy: Creating Value Through Machine Learning and Publicly Available Data Streams by Vahid Moosavi, ETH Zurich
on topics in Big Data Streams, Applied Machine Learning, Deep Learning, Coding as Literacy, and Computational Modeling:
In this rather dense presentation, while I briefly discuss the advantages of a certain category of data driven models over classical theory driven models, I focus on three projects in different fields:
(a) natural language processing and news analysis,
(b) real estate market as a media business and
(c) global city network analysis.
All of these projects are using publicly available data streams such as Twitter feeds, real estate advertisements and Open Street Map.
While seemingly from different domains, we will see how similar skills are required in all of these applications, which is the main argument for what we call “coding as literacy”.
In technical terms related to theme of the meeting, I will briefly show the application of different frameworks and libraries such as Scikit-learn, Gensim and Tensorflow for the machine learning parts and different APIs, flask and beautiful soup for data collection, web crawling and web application development.
Biography: Previously trained and practiced as a systems engineer, currently I am a postdoc researcher at the chair for Computer Aided Architectural Design (CAAD), ETH Zurich. In my PhD I was focused on theories of computational modeling and issues of “representation” and “idealization” in complex systems.
From last semester I have started teaching “Data Driven Modeling” to graduate architecture and design students at ETH. Parallel to this, I am concentrated on several applied machine-learning projects.
I have conducted several research projects in different fields 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 works, please visit me at www.vahidmoosavi.com