IEEE

ISACPP: Interference-Aware Scheduling Approach for Deep Learning Training Workloads Based on Co-Location Performance Prediction

Abstract: Traditional exclusive cloud resource allocation for deep learning training (DLT) workloads is unsuitable for advanced GPU infrastructure, leading to resource under-utilization. Fortunately, ...
eLife

Separating selection from mutation in antibody language models

This important study introduces a new biology-informed strategy for deep learning models aiming to predict mutational effects in antibody sequences. It provides solid evidence that separating ...
GitHub

Conformal Risk Training: End-to-End Optimization of Conformal Risk Control

Download the dataset here, and unzip the dataset to polyps/data. We use a similar dataset as PraNet, with improved pre-processing and filtering of duplicates. See polyps/process_data.ipynb for details ...
IEEE

Cardiac Output Quantification via Esophageal Photoplethysmography and Deep Learning

Abstract: Continuous minimally invasive cardiac output (CO) measurement via photoplethysmography (PPG) has received much attention in daily monitoring. However, the precision of current research is ...
TMCnet

Bridging Silence: A Real-Time Sign Language to English Text Translation System Using Python, OpenCV, and Convolutional Neural Networks

Bridging communication gaps between hearing and hearing-impaired individuals is an important challenge in assistive technology and inclusive education. In an attempt to close that gap, I developed a ...