May 17 (Tue) @ 4:00pm: "Towards Efficient and Robust Neuromorphic Computing Systems," Ling Liang, ECE PhD Defense

Date and Time
Zoom Meeting – Meeting ID: 593 757 8108


Spiking neural networks (SNNs) are known as the third generation of neural networks. For an SNN, the bio-inspired neural dynamics endow the great potential to simulate the neural behaviors of the brain; the additional temporal information propagation provides a larger space to make a comprehensive decision; the binary format and the sparse activities of spikes make SNNs quite energy efficient when considering the real deployment. High accuracy, high efficiency, and high robustness are several attractive features of the brain.

Recently, the emerging supervised training algorithms inspired by backpropagation through time (BPTT) have successfully boosted the accuracy. However, the implementation complexity of these BPTT-based algorithms is explosively growing, which raises a much higher demand for hardware resources. To improve the training efficiency, in this talk I will present two solutions to optimize the BPTT-based training. The first solution is to directly design an ASIC accelerator for SNNs while the other is to optimize the dataflows on GPU.

On the other side, how to improve the robustness of SNNs against adversarial attacks is critical for building a reliable neuromorphic system. In this talk, I will first discuss how to disturb an SNN model through adversarial examples, and then conduct an in-depth analysis of the SNN robustness. With the observations, I will present a robust training method for SNNs inspired by the robustness certification in neural networks.


Ling Liang received the B.E. degree from Beijing University of Posts and Telecommunications, Beijing, China in 2015, and M.S. degree from University of Southern California, CA, USA in 2017. He is currently pursuing the Ph.D. degree at the Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA. His current research interests include spiking neural networks, machine learning security, and cryptography.

Hosted by: Peng Li and Yuan Xie

Submitted by: Ling Liang <>