Key ICML 2018 Takeaways

I had the pleasure of attending this year’s edition of the International Conference on Machine Learning which was held in Stockholm,  Sweden. I was showcasing the Intel Smart Park solution which is an AI system that is meant to assist drivers in finding available parking slots in a parking lot. It is basically a 5-layer CNN which determines whether a slot is available or not and the candidates of available parking slots are passed through a graph algorithm to determine the one that is closest and most convenient for the driver. This is integrated to the car’s HUD and it will provide the driver with instructions to navigate to the assigned spot. You can see the demo  displayed in the background.icml1

In addition to this, I was able to attend a number of very intriguing presentations at the conference the most memorable being the presentation by Sanjeev Arora from Princeton  titled Toward Theoretical Understanding of Deep Learning. He covered topics around optimization for neural nets, Overparametrization/Generalization wrt to parameters and the role of depth i.e how to accelerate optimization by making network deeper. The video recording and presentation for this session are available here .  I highly recommend this for presentation for the invaluable insights he offered on the aforementioned topics. I am still reviewing the rest of my notes from ICML and will update this blog post in due course. In the meantime,below is the picture of a very benevolent autonomous robot from Nvidia that was dishing our candies to the attendees at the conference. Bless it’s soul 🙂

icml2

 

 

 

 

Leave a Reply

Your email address will not be published. Required fields are marked *