Psychology Today

Thinking Upside Down

So, when structure arrives first, it carries a sense of authority. The answer appears already assembled, already confident.
IEEE

Communication-Efficient Network Topology in Decentralized Learning: A Joint Design of Consensus Matrix and Resource Allocation

Abstract: In decentralized machine learning over a network of workers, each worker updates its local model as a weighted average of its local model and all models received from its neighbors.
Open Heart

Development and validation of a deep learning model for severe mitral stenosis detection from chest X-rays

Background Although chest X-rays (CXRs) are widely used, diagnosing mitral stenosis (MS) based solely on CXR findings remains ...
Scientific Research Publishing

Early Alzheimer’s Disease Detection from Short Speech Samples Using Lightweight, Interpretable Linguistic Markers ()

Based Detection, Linguistic Biomarkers, Machine Learning, Explainable AI, Cognitive Decline Monitoring Share and Cite: de Filippis, R. and Al Foysal, A. (2025) Early Alzheimer’s Disease Detection from ...
IEEE

Evaluation of Predictive System of Dropout Risk in Alternative Learning System Using Technology Acceptance Model and Confusion Matrix Analysis

Abstract: This study aims to evaluate the developed predictive dropout risk model in the Alternative Learning System (ALS) by analyzing various demographic, socio-economic, academic, and behavioral ...
GitHub

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

CUDA-L2 is a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. CUDA-L2 ...