Alexander Amini

Alexander Amini email: amini@mit.edu
room: 32-376
resume, google scholar

Bio

I am a PhD student at the Massachusetts Institute of Technology (MIT), in the Computer Science and Artificial Intelligence Laboratory (CSAIL), with Prof. Daniela Rus. I am a NSF Fellow and completed my Bachelor of Science and Master of Science in Electrical Engineering and Computer Science at MIT, with a minor in Mathematics.

My research focuses on building machine learning algorithms for end-to-end control (i.e., perception to actuation) of autonomous systems and formulating guarantees for these algorithms. I have worked on control of autonomous vehicles, formulating confidence of deep neural networks, mathematical modeling of human mobility, as well as building complex inertial refinement systems.

In addition to research, I am also a lead organizer and lecturer for MIT 6.S191: Introduction to Deep Learning, MIT's official introductory course on deep learning. In high school I was named the European Union Young Scientist of 2011 with my project entitled: Tennis Sensor Data Analysis: An Automated System for Macro Motion Refinement. I grew up in New York, and then moved to Dublin, Ireland, where I attended Castleknock College, and then returned to the US in 2012.

My professional resume can be found here.

Projects

Some of my recent projects.

Teaching

Academic courses I teach.

Blog

Blog about my research.

News

Oct 2018   Invited Talk and contributed papers at ICML 2019 Workshop for Autonomous Driving, and Reinforcement Learning in Real Life.
Mar 2019   Our paper Variational End-to-End Navigation and Localization has been nominated for the Best Paper Award at ICRA 2019 (top 0.1% of all submissions)
Jan 2019   Paper: Variational End-to-End Navigation and Localization has been accepted to ICRA 2019.
Jan 2019   Lecturer for the 2nd straight year of MIT 6.S191: Introduction to Deep Learning, MIT's official course on deep learning applications and foundations. [link] [video]
Dec 2018   Paper: Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure has been accepted to AAAI/ACM AIES 2019 [paper]
Oct 2018   Invited Talk at IROS in Madrid, Spain: Variational Autoencoder for End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasing
Jun 2018   Paper: Variational Autoencoder for End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasing has been accepted to IROS 2018 [paper]