activity
20172021
most citedCirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices

177 citations · 196 across the 9 of their papers we have counts for

collaborators

19 papers

cs.NE2021

In-Hardware Learning of Multilayer Spiking Neural Networks on a Neuromorphic Processor

Amar Shrestha, Haowen Fang, Daniel Patrick Rider +2

Although widely used in machine learning, backpropagation cannot directly be applied to SNN training and is not feasible on a neuromorphic processor that emulates biological neuron…

cs.AR2021

Neuromorphic Algorithm-hardware Codesign for Temporal Pattern Learning

Haowen Fang, Brady Taylor, Ziru Li +3

Neuromorphic computing and spiking neural networks (SNN) mimic the behavior of biological systems and have drawn interest for their potential to perform cognitive tasks with high e…

cs.NE20202 cited

Multivariate Time Series Classification Using Spiking Neural Networks

Haowen Fang, Amar Shrestha, Qinru Qiu

There is an increasing demand to process streams of temporal data in energy-limited scenarios such as embedded devices, driven by the advancement and expansion of Internet of Thing…

cs.CV20202 cited

MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level

Amar Shrestha, Krittaphat Pugdeethosapol, Haowen Fang +1

Grounding free-form textual queries necessitates an understanding of these textual phrases and its relation to the visual cues to reliably reason about the described locations. Spa…

cs.RO2020

GISNet: Graph-Based Information Sharing Network For Vehicle Trajectory Prediction

Ziyi Zhao, Haowen Fang, Zhao Jin +1

The trajectory prediction is a critical and challenging problem in the design of an autonomous driving system. Many AI-oriented companies, such as Google Waymo, Uber and DiDi, are…

cs.CV2020

Mission-Aware Spatio-Temporal Deep Learning Model for UAS Instantaneous Density Prediction

Ziyi Zhao, Zhao Jin, Wentian Bai +4

The number of daily sUAS operations in uncontrolled low altitude airspace is expected to reach into the millions in a few years. Therefore, UAS density prediction has become an eme…