1 code implementation • 31 Jan 2024 • R. Alexander Knipper, Kaniz Mishty, Mehdi Sadi, Shubhra Kanti Karmaker Santu
As spiking neural networks receive more attention, we look toward applications of this computing paradigm in fields other than computer vision and signal processing.
no code implementations • 18 Nov 2021 • Mehdi Sadi, B. M. S. Bahar Talukder, Kaniz Mishty, Md Tauhidur Rahman
Universal Adversarial Perturbations are image-agnostic and model-independent noise that when added with any image can mislead the trained Deep Convolutional Neural Networks into the wrong prediction.
no code implementations • 6 Apr 2021 • Kaniz Mishty, Mehdi Sadi
Compared to an SRAM-based implementation, the STT-AI accelerator achieves 75% area and 3% power savings at iso-accuracy.