A while ago I listened to an interesting podcast called the Hidden Brain on the role of outrage in the tribal social balance of trust. Outrage as an emotion played an extremely important role in a tribal society against non-compliant actors. If you got outraged on someone if they betrayed your trust or hoodwinked you, it can quickly translate into a tribal crisis resulting into direct disciplinary consequence, and in most cases depleating the perpetrator of their social capital.
Researchers and practitioners intererested in geography of health, social dynamics, economics, and everything in between are always interested methods that use data to sense health outcomes in the real world. If one can create proxies for health, and map them on to geographical units, one could ask important questions such as: a) How does health of an area relate with its socio-economic conditions? b) Are there any temporal trends or periodicities in certain health outcomes?
After 2.5 years of association with Nokia Bell Labs, I have decided to move on to do something else. I will be moving into a more product oriented data science role at the Expedia Group, from a blue sky research role at Bell labs. Working with such a stellar organization and its brilliant people was truly enriching in so many ways. But it was equally an excercise in self awareness. And the greatest outcome of this excercise, to me, was the awareness of the costs of being on the fence.
Super excited to see that our paper on measuring differential behaviour of ad-tracking ecosystem towards the consumers of hyper-partisan websites was covered by the Wired news. In this paper, we simulated behaviours of users belonging to particular partisan and demographic classes, and observed how the online advertisement machinenary tracks them as they visit well known partisan news websites. To our surprise, we found that the very nature of such automated profiling systems pushes them to preferentially track users with specific partisan lean more.
I am very happy to announce the publication of “FaceLift: a transparent deep learning framework to beautify urban scenes” in the Royal soceity open science journal Facelift is a Deeplearning driven algorithm, that goes beyond assessing beauty in urban scenes (streetviews) – as done by other studies in the field – and recreates the elements that can make any given urban scene more beautiful. It then explains away the elements behind the beauty using metrics which are commonly understood by the target users of this system such as Urban Planners and Architects.
I succesfully defended my Ph.D titled “From Communities to Crowds: Quantifying the subjective”. The examiners recommended minor corrections to the dissertation. The dissertation was examined by Prof. Joemon Jose and Prof. Yulan He I want to sincerely thank Prof. Nishanth Sastry and all the collaborators who have mentored and enriched me in various aspects of being a researcher over the past 4 years. I would also like to thank King's India scholarship and the King's graduate school for supporting me during my tenure at Kings.
I have officially started as a research scientist at Bell labs, Cambridge, UK. I will work with the Social dynamics team on problems dealing with the modelling of different phenomenon in the realms of urban informatics, social health and AI for social good.
Our project FaceLift: A deeplearning pipeline to beautify urban spaces, has been shortlisted in the highly selective EPSRC Pioneers competetion. We are one of the top 16 Ph.D. projects around U.K. It stands in the top 4 projects among the creative computing category. Please find the full announcement here.
We have receieved the Nvidia GPU seed grant, which I wrote on my Lab's behalf. The award would increase Netsys's compute infrastructure with the help of a Nvidia Titan Xp GPU for our deep learning needs