In this talk, we study the adversarial robustness of deep neural networks for classification tasks. We look at the smallest magnitude of possible additive perturbations that can change the output of a classification algorithm.
Come visit the Electrical and Computer Engineering Graduate Student Association (ECE-GSA) in the quad and participate in kid-friendly art activities that demonstrate how semiconductor device fabrication works. Water and fun t-shirts for sale/donation.
As next-generation automobile radars, Internet of Space, and 6G wireless communications push the operation frequency above 110 GHz, compact, high-power, and low-noise sub-THz transceivers are needed to overcome the atmospheric absorption for high data rate, low latency, and high spatial diversity/resolution.
Out-of-Distribution (OOD) detection in machine learning refers to the problem of detecting whether the machine learning model's output can be trusted at inference time.
