One of the biggest challenges to overcome in (research) collaborations is often that people are not in the same place and do not have a common “space” available where one can exchange and discuss, including being able to write math equations, in real-time: a shared digital whiteboard. Recently, I finally found a solution that works well (for my needs) and I thought it might be helpful for others as well.

I have been through numerous iterations, including onenote, overleaf, rudel, google docs, gobby-based chats and many other tools and constructs but all of them fell short in at least one…


Disclaimer: the expressed opinions are my personal ones and are not necessarily those of Georgia Tech or ML@GT. Moreover, the following does not constitute any investment advice.

Full disclosure: I was/am/will be invested in crypto currencies in one way or another.

When is a good time to write about crypto currencies? If the market is up one will be accussed of being self-serving and indulgent, if the market is down and one has tried to catch a falling knife that cut down to the bone, then it is pep talk. I originally wrote (most of) this post several months back…


Disclaimer: the expressed opinions are my personal ones and are not necessarily those of Georgia Tech or ML@GT.

It pretty much does not matter what position one has on Artificial Intelligence (AI) and Machine Learning (ML), but the strong interest in AI and ML can hardly be denied. In fact, doing a quick informal poll among colleagues and friends, it seems that many Thanksgiving table and holiday conversations were dominated by either AI or cryptocurrencies (Bitcoin and the likes). …


It is always great to see your own students being successful after graduation and turning into independent researchers with their own perspective and pursuing their own vision. While at conferences (NIPS in this case), I usually try to catch up and learn about their research and results. And so it comes that this NIPS I learned about some very cool results from Aurko Roy (who is now at Google Brain and graduated from GT in Spring 2017) and co-authors Tom B. Brown, Dandelion Mané, Martín Abadi, and Justin Gilmer (all from Google).

One of the recent hot areas in machine…


This year’s NIPS just started in Long Beach, CA nicely rounding off my time in California. I had a great time at the Simons Institute in Berkeley and learned a lot. Now it is time to head back — after NIPS.

As already last year, NIPS has been sold out several weeks ahead of its start and as such there is no onsite registration (and also all sponsoring spots have sold out as well). This is quite different from some other conferences that I went to in the past: many would register only on-site keeping their options open whether to…


The list of accepted papers at ICML2017 was released yesterday and Andrej Karpathy has published a very nice post breaking down the acceptance by institution. Out of 1701 submissions 433 papers were accepted (or roughly 25.46%) from 420 different institutions. I am excited to see a very strong representation of Machine Learning @ Georgia Tech (ML@GT) with 13 papers (Andrej reported 14 but I could only find 13 — going with the conservative estimate). This brings GT into the Top 10 among institutions and if you only consider academic institutions it is 6th on the list being testament to GT’s…

Sebastian Pokutta

Analytics, Optimization, Machine Learning, Systems AI, and Cyber-Physical Systems. Prof @GeorgiaTech. Assoc. Director @mlatgt.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store