Graph-Structured Kernel Design for Power Flow Learning using Gaussian Processes

P Pareek, D Deka, S Misra - arXiv preprint arXiv:2308.07867, 2023 - arxiv.org
This paper presents a physics-inspired graph-structured kernel designed for power flow
learning using Gaussian Process (GP). The kernel, named the vertex-degree kernel (VDK) …

Ensembles of Informative Representations for Self-Supervised Learning

KD Polyzos, PA Traganitis, MK Singh… - 2024 IEEE 34th …, 2024 - ieeexplore.ieee.org
The requirement of large-size labeled training datasets often prohibits the deployment of
supervised learning models in several applications with high acquisition costs and privacy …

Gaussian Process-based Active Learning for Efficient Cardiovascular Disease Inference

SC Tassi, KD Polyzos, DI Fotiadis… - … on Bioinformatics and …, 2023 - ieeexplore.ieee.org
Cardiovascular disease (CVD) poses a significant global health challenge, and accurate
inference methods are vital for early detection and intervention. However, the quality of …

Simpler Yet Smarter AI: Learn and Optimize With Just a Few Labeled Data

K Polyzos - 2024 - search.proquest.com
Abstract Machine learning (ML) has gained popularity due to its well-documented merits in
several inference tasks across diverse applications including healthcare, robotics and …