no code implementations • 17 Jul 2023 • Dongning Ma, Xun Jiao, Fred Lin, Mengshi Zhang, Alban Desmaison, Thomas Sellinger, Daniel Moore, Sriram Sankar
Deep recommendation systems (DRS) heavily depend on specialized HPC hardware and accelerators to optimize energy, efficiency, and recommendation quality.
no code implementations • 23 Sep 2022 • Dongning Ma, Pengfei Zhao, Xun Jiao
Neural Architecture Search (NAS) is an automated architecture engineering method for deep learning design automation, which serves as an alternative to the manual and error-prone process of model development, selection, evaluation and performance estimation.
no code implementations • 24 Jul 2022 • Dongning Ma, Xun Jiao
Hyperdimensional Computing (HDC) has obtained abundant attention as an emerging non von Neumann computing paradigm.
no code implementations • 25 Mar 2022 • Ruixuan Wang, Dongning Ma, Xun Jiao
Ensemble learning is a classical learning method utilizing a group of weak learners to form a strong learner, which aims to increase the accuracy of the model.
no code implementations • 7 Feb 2022 • Dongning Ma, Sizhe Zhang, Xun Jiao
We formulate the model development of HDC as a problem that can be used in blockchain mining.
no code implementations • 5 Jun 2021 • Dongning Ma, Rahul Thapa, Xun Jiao
In this paper, we propose a viable alternative to existing learning methods by presenting MoleHD, a method based on brain-inspired hyperdimensional computing (HDC) for molecular property prediction.
no code implementations • 26 May 2021 • Rahul Thapa, Dongning Ma, Xun Jiao
In this paper, we systematically expose the unexpected or incorrect behaviors of HDC models by developing HDXplore, a blackbox differential testing-based framework.
no code implementations • 15 Mar 2021 • Dongning Ma, Jianmin Guo, Yu Jiang, Xun Jiao
Using handwritten digit classification as an example, we show that HDTest can generate thousands of adversarial inputs with negligible perturbations that can successfully fool HDC models.
no code implementations • 8 Feb 2021 • Dongning Ma, Meltem Izzetoglu, Roee Holtzer, Xun Jiao
However, the automatic classification of differences in cognitive activations under single and dual task gait conditions has not been extensively studied yet.