Chang Gao receives the Mahowald Early Career Award for Neuromorphic Engineering

The MECA jury has awarded the 2022 Mahowald Early Career Award to Chang Gao (Assistant Professor in ELCA) for the project "Accelerating Recurrent Neural Networks with Neuromorphic Principles." The project introduces efficient computing using the neuromorphic principles of spatial and temporal sparsity, leading to an energy-efficient accelerator for edge RNN computing. Gao's accomplishments have the potential to revolutionize applications in healthcare, wearables, and intelligent biomedical implants.

The Mahowald Early Career Award (MECA) recognizes an exceptionally talented student, as Misha Mahowald was. The Award is made for an innovative project that addresses a significant problem in neuromorphic engineering or related problems in neuroscience and neural computation. In their submission, candidates must make a convincing case for why their project fulfills this criterion.

Gao developed this work during his Ph.D. with the Sensors Group at the Institute of Neuroinformatics, University of Zurich and ETH Zurich. He is now a tenure-track assistant professor at TU Delft, where he has started a lab entitled "Efficient circuits & systems for Machine Intelligence" (EMI). Gao's Google scholar profile provides links to his work.


More ...

CAS becomes SPS

The Circuits and Systems (CAS) group was formed over 20 years ago out of a merger of the Electronic Techiques and the Network Theory group. The resulting group had a focus on system theory and digital VLSI design, in particular design and verification tools.

Over these years, the signal processing part of the group has grown, to a point where now it is time to change our name. Starting from 1 January 2023, the group is called Signal Processing Systems (SPS). Happy New Year!

More ...

NWO OTP Award SMARTER: Strategic Monitoring of Atmospheric Threats using Enhanced Radar

TU Delft researchers dr. Francesco Fioranelli (ME-MS3) and dr. Marc Schleiss (CITG-GRS) receive NWO OTP funding for a four year research on strategic monitoring of atmospheric threats.
Atmospheric threats such as heavy rain and hail, are responsible for millions of damages in the Netherlands every year. Weather radars are essential tools to study the atmosphere, monitor threats, and issue early warnings for high impact events. The frequency of a radar and its configuration determine what type of weather phenomena can be measured, at which resolution and accuracy. To maximize coverage while simultaneously gathering lots of details about the small-scale structure and dynamics of local rain/hail events, different types of radars can be combined into larger networks. The crucial piece that is missing is a ‘central control unit’ for coordinating the efforts of each radar in the network.

In the project SMARTER Francesco and Marc with their teams will develop a new AI-based control unit for maximizing the collaboration between individual radars in a network and improve the detection/prediction of localized, rapidly developing atmospheric threats while keeping the large-scale overview of the situation. For a first proof of concept, the focus will be on detecting heavy rain and hail in the Greater Rotterdam area, which is of major interest for the horticultural industry and the Dutch economy in general. However, the novel adaptation and decision-making tool will be sufficiently general to be transferable to other networks outside the Netherlands and other targets such as insects, birds and aircrafts.

This project is executed in collaboration with the following partners: Glastuinbouw Nederland, Achmea Agro, KNMI, SkyEcho, Leonardo, RPG and HKV.

More ...