The EMI Lab - TU Delft
The Efficient circuits & systems for Machine Intelligence (EMI) research lab focuses on designing energy-efficient digital AI hardware for edge computing, emphasizing ultrahigh-speed communication, video/audio processing, robotics, and biomedical applications. We aim to bridge the gap between artificial neural networks (ANNs) and spiking neural networks (SNNs) by applying brain-inspired neuromorphic principles to massively accelerate the computation of state-of-the-art deep neural network (DNN) architectures while maintaining competitive accuracy on real-world tasks (We are hiring!).
130K Swiss Francs Fund Received by Our Partner
August 29, 2022
We congratulate Dr. Qinyu Chen again for winning the BRIDGE Proof of Concept grant for her postdoctoral project. The 130,000 CHF fund will be released by the Swiss National Science Foundation (SNSF) and Innosuisse - Swiss Innovation Agency. The EMI lab will collaborate with Dr. Qinyu Chen, a Postdoctoral Researcher in the Sensors Group at the Institute of Neuroinformatics, University of Zurich and ETH Zurich to build next-generation edge AI chips for healthcare.
New TVLSI Paper on Accelerating Spiking Neural Networks
August 17, 2022
We congratulate Dr. Qinyu Chen and other co-authors for publishing the paper "Cerebron: A Reconfigurable Architecture for Spatio-Temporal Sparse Spiking Neural Networks" in the IEEE Transactions on Very Large Scale Integration Systems (TVLSI). See our paper at this link.
Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator Exploiting Spatio-Temporal Sparsity (2022)
A 23μW Solar-Powered Keyword-Spotting ASIC with Ring-Oscillator-Based Time-Domain Feature Extraction (2022)
How to Find Us
Address: Electronic Circuits and Architecture Group, TU Delft, Fac. EEMCS, Mekelweg 4, 2628 CD Delft, Netherlands
Email: chang.gao at tudelft.nl
TU Delft Page: http://microelectronics.tudelft.nl/People/bio.php?id=840