Alexander Amini

Alexander Amini email: amini@mit.edu
room: 32-376
CV // google scholar // bio

Bio

I am a Postdoctoral Research Associate at the Massachusetts Institute of Technology (MIT), in the Computer Science and Artificial Intelligence Laboratory (CSAIL), with Prof. Daniela Rus. I completed my PhD (2022), Master of Science (2018), and Bachelor of Science (2017) in Computer Science at MIT, with a minor in Mathematics.

The objective of my research is to develop the science and engineering of autonomy and its applications to safe decision making for autonomous agents. My vision is a world with adaptive autonomous agents capable of learning to interact in complex, uncertain, and extreme scenarios, supporting people with cognitive and physical tasks. I have worked on learning end-to-end control (i.e., perception-to-actuation) of autonomous systems, formulating confidence of 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 awarded the first place Grand Prize at the EU Content for Young Scientists and BTYSTE 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.

Please click here for my curriculum vitae (CV) or a third-person bio.

Projects

Some of my recent projects

Publications

My latest published research

Teaching

Courses, students, & mentorship

News

Oct 2021   Paper: Two new papers accepted to NeurIPS 2021 on the topics of causual navigation models [paper] and sparse flows [paper]!
Apr 2021   Our paper on co-optimizing sensor placement and policy learning is accepted to RA-L and nominated for the Best Paper Award at RoboSoft 2021! [paper] [news]
Mar 2021   Two new papers using our evidential uncertainty algorithm have been accepted and published for improved robustness in molecular drug discovery [paper] and end-to-end autonomous driving [paper]!
Feb 2021   Awarded two grants with FinTech@CSAIL and MachineLearningApplications @CSAIL to mitigate algorithmic bias and uncertainty in financial time series modeling and clinical trial outcome prediction.
Jan 2021   Lead organizer and lecturer for MIT 6.S191: Introduction to Deep Learning, with over 700 registered MIT students (and over 30,000 registrations globally online). [link] [video]
Dec 2020   Awarded the JP Morgan Fellowship for the 2021-2022 academic year with a focus on robustness and uncertainty of learning-based systems!
Dec 2020   Our paper on liquid time-constant neural networks is accepted to AAAI with an Oral spotlight! [paper] [news]
Aug 2020   Two papers focused on uncertainty and robustness of ML! (1) published in Nature Machine Intelligence and (2) accepted at NeurIPS for presentation in Dec 2020.