IEEE CIS & CS Schenectady Chapters Technical Lecture on "Efficient Learning for Control and Sensing"

#AI, #MachineLearning, #ControlSystems, #Robotics, #AutonomousSystems, #BayesianModeling, #GaussianProcesses, #SignalProcessing, #InverseProblems, #SchenectadyIEEE, #IEEE_CIS, #IEEE_CS
Share

"Efficient Learning for Control and Sensing "

I will present safe learning methods for autonomy that combine Bayesian modeling with control barrier formulations to enable real-time safety and online adaptation. I will then introduce DAREK, a distance-aware uncertainty model that offers a computationally efficient alternative to Gaussian-process-based approaches. Next, I will move from control to sensing and inverse problems. I will discuss how invertible architectures enable efficient posterior inference, and how symbolic invertibility can further improve interpretability. I will illustrate these ideas on an inverse problem in ocean-acoustic sensing. 


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar

Loading virtual attendance info...

  • Contact Event Hosts
  • Co-sponsored by IEEE CIS and CS Schenectady Chapter
  • Starts 10 March 2026 04:00 AM UTC
  • Ends 18 March 2026 09:00 PM UTC
  • No Admission Charge

  Speakers

Mohammad Javad of Rochester Institute of Technology

Topic:

Efficient Learning for Control and Sensing

In this talk, the speaker will present safe learning methods for autonomy that combine Bayesian modeling with control barrier formulations to enable real-time safety and online adaptation. I will then introduce DAREK, a distance-aware uncertainty model that offers a computationally efficient alternative to Gaussian-process-based approaches. Next, I will move from control to sensing and inverse problems. I will discuss how invertible architectures enable efficient posterior inference, and how symbolic invertibility can further improve interpretability. I will illustrate these ideas on an inverse problem in ocean-acoustic sensing.

Biography:

 

Dr. Mohammad Javad Khojasteh received the Ph.D. and M.Sc degrees in Electrical and Computer Engineering from University of California San Diego in 2019 and 2017, respectively. He is a Gleason Endowed Assistant Professor at Rochester Institute of Technology (RIT). Before joining RIT, he held postdoctoral positions at Marine Physical Laboratory (MPL) at Scripps Institution of Oceanography (SIO), Department of Mechanical Engineering and Laboratory for Information and Decision Systems (LIDS) at Massachusetts Institute of Technology (MIT), and Center for Autonomous Systems and Technologies (CAST) at California Institute of Technology (Caltech), where he worked with Team CoSTAR as visitor at NASA Jet Propulsion Laboratory. He received the Gleason Chair in 2024 and the 2025 Provost’s Learning Innovation Grant at RIT. Dr. Khojasteh's publications, co-authored with colleagues and students, have received awards, including Tammy L. Blair Student Paper Award (second place) from the International Society of Information Fusion.

Email: