College of Computing - Georgia Tech

Ph.D. Student’s Framework Used to Bolster Nvidia’s Cosmos Predict-2 Model

Nvidia used NATTEN to fine-tune its prediction model, Cosmos Predict, and the company introduced the second version of the ...
Wall Street Journal

I Trained for the Marathon with Artificial Intelligence. But the Suffering Was Real.

When I crossed the finish line of the New York City Marathon, some four hours after starting and four months after enlisting ChatGPT as my coach, I burst into tears. Everything hurt. I was also in ...
Tech Xplore

Smart sensor network and AI algorithms ease strain on stressed drivers

Fraunhofer researchers have developed a system that uses sensors and AI to monitor a driver's cognitive load. In the future, ...
Devdiscourse

AI-Driven Hybrid Models Forecast China’s Energy and Fuel Use for a Greener Future

The study by researchers from Jiangxi’s universities introduces hybrid machine learning models optimized with Artificial ...

Machine learning workflow enables faster, more reliable organic crystal structure prediction

Prediction of crystal structures of organic molecules is a critical task in many industries, especially in pharmaceuticals ...
AlphaGalileo

Faster and More Reliable Crystal Structure Prediction of Organic Molecules

Crystal structure prediction (CSP) of organic molecules is a critical task, especially in pharmaceuticals and materials ...
Scientific Research Publishing

Research on Prediction of Air Quality CO Concentration Based on Python Machine Learning ()

Wang, Z. (2025) Research on Prediction of Air Quality CO Concentration Based on Python Machine Learning. Advances in Internet ...
Scientific Research Publishing

Estimating Average and Heterogeneous Effects of Special Education: A Causal Machine Learning Perspective ()

Causal Machine Learning (CML) unites ML techniques with CI in order to take advantage of both approaches’ strengths. CML ...
eLife

CellCover Defines Marker Gene Panels Capturing Developmental Progression in Neocortical Neural Stem Cell Identity

This study offers a valuable methodological advance by introducing a gene panel selection approach that captures combinatorial specificity to define cell identity. The findings address key limitations ...
Communications of the ACM

Shields for Safe Reinforcement Learning

Evaluating the advantages and potential drawbacks of shielding as a method for safe RL. Bettina Könighofer is an assistant ...
IEEE

Optimizing XGBoost Hyperparameters for Credit Scoring Classification Using Weighted Cognitive Avoidance Particle Swarm

Abstract: Decision trees in machine learning achieved satisfactory performance in classification. Decision trees offer the advantage of handling high-dimensional and complexly correlated data through ...
TheServerSide

Google Professional Machine Learning Engineer Certification Practice Exams

First, pick your designation of choice. In this case, it’s Google’s Professional Machine Learning Engineer certification. Then look up the exam objectives and make sure they match your career goals ...