activity
20202023
most citedSparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm

8 citations · 21 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2023

Efficient and Direct Inference of Heart Rate Variability using Both Signal Processing and Machine Learning

Yuntong Zhang, Jingye Xu, Mimi Xie +3

Heart Rate Variability (HRV) measures the variation of the time between consecutive heartbeats and is a major indicator of physical and mental health. Recent research has demonstra…

cs.LG2023

PPG-based Heart Rate Estimation with Efficient Sensor Sampling and Learning Models

Yuntong Zhang, Jingye Xu, Mimi Xie +4

Recent studies showed that Photoplethysmography (PPG) sensors embedded in wearable devices can estimate heart rate (HR) with high accuracy. However, despite of prior research effor…

cs.LG2022★ 1 cited

Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off

Shaoyi Huang, Bowen Lei, Dongkuan Xu +4

Over-parameterization of deep neural networks (DNNs) has shown high prediction accuracy for many applications. Although effective, the large number of parameters hinders its popula…

cs.LG2022

EVE: Environmental Adaptive Neural Network Models for Low-power Energy Harvesting System

Sahidul Islam, Shanglin Zhou, Ran Ran +4

IoT devices are increasingly being implemented with neural network models to enable smart applications. Energy harvesting (EH) technology that harvests energy from ambient environm…

cs.LG2021

Enabling Fast Deep Learning on Tiny Energy-Harvesting IoT Devices

Sahidul Islam, Jieren Deng, Shanglin Zhou +3

Energy harvesting (EH) IoT devices that operate intermittently without batteries, coupled with advances in deep neural networks (DNNs), have opened up new opportunities for enablin…

cs.LG2021★ 4 cited

Binary Complex Neural Network Acceleration on FPGA

Hongwu Peng, Shanglin Zhou, Scott Weitze +9

Being able to learn from complex data with phase information is imperative for many signal processing applications. Today' s real-valued deep neural networks (DNNs) have shown effi…