March 9th, 2021
[New Preprint] A new preprint of our work on comparing model-based to model-free agents in autonomous racing environments is out![link]
March 1st, 2021
[Accepted Papers] [ICRA 2021] our works “Adversarial training is not ready for robot learning” have been accepted for publication at the IEEE International Conference on Robotics and Automation (ICRA) 2021. [link]
January 28th, 2021
[Press] MIT News article about our research: “Liquid” machine-learning system adapts to changing conditions.
The new type of neural network could aid decision-making in autonomous driving and medical diagnosis. [link]
December 2nd, 2020
[2 Accepted Papers] [AAAI 2021] our works entitled “Liquid Time-constant networks” and “On the verification of Neural ODEs” have been accepted for publication at the Association for the Advancement of Artificial Intelligence (AAAI) 2021 Conference. [link]
September 28th, 2020
[Postion Update] I joined the Distributed Robotics Lab (DRL) of CSAIL MIT, as a postdoctoral associate.
September 10th, 2020
[Accepted Paper] Neural Circuit Policies Enabling Auditable Autonomy got accepted for publication in Nature Machine Intelligence.
June 1st, 2020
Accepted Paper] Our paper “The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits” got accepted to the 2020 International Conference on Machine Learning (ICML).
May 13th, 2020
[PhD dissertation] Check out my PhD dissertation here: [link]
May 5th, 2020
I have completed my doctorate (PhD) studies with distinction!
Jan 30th, 2020
[Accepted paper] Gershgorin loss stabilizes the RNN compartment of a robotics learning system is accepted to ICRA 2020.
Mar 5th, 2019
[Accepted paper] We proposed a new method to interpret LSTM networks. The work is accepted to the 32nd International Joint Conference on Neural Networks (IJCNN) 2019. [link]
Feb 26th, 2019
[MIT] I will be back at MIT CSAIL Daniela Rus’s Robotics Lab as a research scholar, as of March 2019. We will be working on developing interpretable machine learning algorithms for autonomous systems.
January 26th, 2019
[Accepted Paper] ICRA 2019 – We proposed a new brain-inspired neural network design methodology for interpretable and noise-robust robotic control [link]
November 29th, 2018
[TED Talk] My TEDxVienna talk is officially released by TEDx. watch it [here]
November 16th, 2018
[Accepted Paper] We proposed a new method to interpret LSTM networks. The paper will be presented at the NeurIPS (NIPS) 2018 Workshop on Interpretability and Robustness (IRASL). [Paper]
November 12th, 2018
[Interview] Read my interview with Vera Steiner at TEDxVienna here
November 1st, 2018
[Accepted paper] “A Machine Learning Suite for Machine Components’ Health-Monitoring” got accepted for an oral presentation at the Thirty-First AAAI conference on Innovative Applications of Artificial Intelligence (IAAI 2019), Honolulu, Hawaii, USA, 2019.
October 12th, 2018
[Google Cloud Credits] Google Cloud Platform (GCP) Research Credit Program ($13,085),[link]
September 11th, 2018
[Accepted papers] 2 journal papers got published at the Royal Society Philosophical Transactions: Biological Sciences. [Publications]
June 20th, 2018
[MIT Press] In a recently accepted paper at the Robotics Sicence and Systems (RSS) 2018 Conference, we show “How to control robots with brainwaves and hand gestures” [MIT Press release][Paper]
June 15th, 2018
[Presentation] At ICML & IJCAI 2018 conferences, I will present “Interpretable Neuronal Circuit Policies for Reinforcement Learning Environments” at the Explainable AI (XAI-18) workshop and “A Machine Learning Suite for Machine Components’ Health-Monitoring” at DISE1 workshop.
January 29th, 2018
[Granted Award] Microsoft Azure for Research award, value: $13000 [link]
October 5th, 2017
[Granted Award] Sponsor Scholar at NIPS 2017
September 10th, 2017
[WNIP Workshop at NIPS 2017] I am co-organizing the first edition of the NIPS-2017 workshop on Worm’s Neural Information Processing (WNIP)
August 21th, 2017
[IJCAI BOOM 2017 Best Poster Award] My poster won the best poster award at the IJCAI 2017 International Workshop on Biomedical Informatics with Optimization and Machine learning (BOOM). [link]
August 6th, 2017
[ICML Award] Listed as one of the 217 sponsor scholars at the ICML 2017 [Link]
June 29th, 2017
A report on our activities on the nervous system of the worm, C. elegans, is published in the first edition of the Austrian Computer Society (OCG) Journal.
June 16th, 2017
[Accepted Paper] One paper at Workshop on Computational Biology (WCB 2017), 34th International Conference on Machine Learning (ICML). see publications for more details
June 14th, 2017
Chaired the “Spiking Neurons” session at 14th International Work-Conference on Artificial Neural Networks (IWANN2017) Conference program
June 5th, 2017
[Accepted Paper] One short paper at 2nd International Workshop on Biomedical Informatics with Optimization and Machine Learning (BOOM 2017), In conjunction with 26th International Joint Conference on Artificial Intelligence (IJCAI). see publications for more details
April 7th, 2017
[Accepted Paper] Two papers at 14th International Work-Conference on Artificial Neural Networks (IWANN2017). see publications for more details
April 3rd, 2017
[Simple-AI] Read about our bio-machine learning activities and projects at simple-ai.com
March 23rd, 2017
[Blogging for OpenWorm] Check out the new Github issue on the simulation of the worm’s crawling here
February 3rd, 2017
[Accepted Paper] at the 30th International Joint Conference on Neural Networks (IJCNN2017). see publications for more details
January 27th, 2017
We are planning to open a new course on deep learning at Cyber-Physical-Systems Group
I am preparing a 3 ECTS course on deep learning for the next academic year 2017-2018.
January 12th, 2017
Microsoft Azure Research Award is Granted for our Research
We have been awarded a Microsoft Azure sponsorship with a value of $20,000.00 for using state-of-the-art cloud services provided by Microsoft for our research!
This award enables us to access Azure NC-based Virtual Machine instances which are powered by NVIDIA Tesla® K80 GPUs and provide the computing power required to accelerate the most demanding high-performance computing (HPC) and AI workloads. Cloud computing lets you spend more time on your research, providing all the computing you need, exactly when you need it. Whether it’s a computer with more memory, a cluster with thousands of cores, a big data platform, an internet of things solution, or open-source machine learning at scale, you can achieve more using the cloud. Microsoft Azure for Research awards offer large allocations of cloud computing for your research project, and already supports hundreds of researchers worldwide across all domains.
Ramin M. Hasani
Cyber Physical Systems Group
December 3rd, 2016
My talk at OpenWorm Journal Club: The Search For Food
Dr. Stephen Larson from the OpenWorm Foundation and I have led a live discussion about a recent work describing a model for predicting C. elegans random search behavior. The paper to be discussed is “A stochastic neuronal model predicts random search behaviors at multiple spatial scales in C. elegans” by W. Roberts, et. al.
[Link to the event]
To boldly go where no worm has gone before. This is the research that seeks to model and deepen our understanding of how the neural circuitry of C. Elegans drives the worm to seek out new potential food sources.In this edition of the OpenWorm Journal Club, we discuss recent work describing a model for predicting C Elegans random search behavior. The paper to be discussed is “A stochastic neuronal model predicts random search behaviors at multiple spatial scales in C. elegans” by W. Roberts, et. al., and the discussion will be led by Dr. Ramin Hasani from the Vienna University of Technology, and Dr. Stephen Larson from the OpenWorm Foundation.
Published January 29, 2016
Cite as eLife 2016;5:e12572
“Random search is a behavioral strategy used by organisms from bacteria to humans to locate food that is randomly distributed and undetectable at a distance. We investigated this behavior in the nematode Caenorhabditis elegans, an organism with a small, well-described nervous system. Here we formulate a mathematical model of random search abstracted from the C. elegans connectome and fit to a large-scale kinematic analysis of C. elegans behavior at submicron resolution. The model predicts behavioral effects of neuronal ablations and genetic perturbations, as well as unexpected aspects of wild-type behavior. The predictive success of the model indicates that random search in C. elegans can be understood in terms of a neuronal flip-flop circuit involving reciprocal inhibition between two populations of stochastic neurons. Our findings establish a unified theoretical framework for understanding C. elegans locomotion and a testable neuronal model of random search that can be applied to other organisms.”