Phil 6.23.18

Registered for SASO

ArXive papers with Github repos

Mapping interest communities in Russian Facebook Ads. Preliminary visualisation reveals a number of broad interest groups around ethnicity; reveals a bit of Internet Research Agency’s strategy...

  • Dr Bharath Ganesh
    • Bharath is a political geographer focusing on data science and local government and the ethics and politics of researching violent online extremism.

More good stuff from Ian Couzin

  • Revealing the hidden networks of interaction in mobile animal groups allows prediction of complex behavioral contagion
    • We know little about the nature of the evolved interaction networks that give rise to the rapid coordinated collective response exhibited by many group-living organisms. Here, we study collective evasion in schooling fish using computational techniques to reconstruct the scene from the perspective of the organisms themselves. This method allows us to establish how the complex social scene is translated into behavioral response at the level of individuals and to visualize, and analyze, the resulting complex communication network as behavioral change spreads rapidly through groups. Thus, we can map, for any moment in time, the extent to which each individual is socially influential during collective evasion and predict the magnitude of such behavioral epidemics before they actually occur

This playlist contains tutorials to learn how to use Keras, a neural network API written in Python. Each video focuses on a specific concept and shows how the full implementation is done in code using Keras and Python.