Towards a Convergence-Informed Toolflow for Accelerating Gaussian Belief Propagation

Add to your list(s) Download to your calendar using vCal

• Omar Sharif (Imperial College)
• Monday 20 May 2024, 13:00-14:00
• Department of Electrical and Electronic Engineering, Room 909B.

If you have a question about this talk, please contact George A Constantinides.

Gaussian Belief Propagation (GBP) is an iterative method of factor graph inference that provides an approximate solution to the probability distribution of a system, with broad applications in fields such as SLAM and Image Denoising. Our ongoing work has produced a toolflow capable of selecting optimal hardware design parameterizations given the properties of the input graph and the available FPGA resources. In this seminar, we will explore this toolflow and discuss how properties of GBP are leveraged to maximize the raw performance of the system. In addition, we will introduce our current research investigating how GBP convergence dynamics may be used to enhance our toolflow’s design space exploration.

This talk is part of the CAS Talks series.

This talk is included in these lists:

• Andrea Picciau's list
• CAS Talks
• Circuits and Systems Group: Internal Seminars
• Department of Electrical and Electronic Engineering, Room 909B

Note that ex-directory lists are not shown.