From the 1 of 5 linked papers with an AI index.
5 papers
Beyond Static Costs: Learning-Dynamics Aware Loss Functions for Long-Tailed Classification
Varad Shinde, Nikhil Kumar Shrey, Magesh Rajasekaran +5
The paper introduces a Learning‑Dynamics Aware Loss (LDAL) that continuously adjusts class weights during training based on feature strength, prediction entropy, and inter‑epoch ch…
Benchmarking Artificial Intelligence Models for Daily Coastal Hypoxia Forecasting
Magesh Rajasekaran, Md Saiful Sajol, Chris Alvin +3
Coastal hypoxia, especially in the northern part of Gulf of Mexico, presents a persistent ecological and economic concern. Seasonal models offer coarse forecasts that miss the fine…
COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification
Magesh Rajasekaran, Md Saiful Islam Sajol, Frej Berglind +2
Identifying out-of-distribution (OOD) data at inference time is crucial for many machine learning applications, especially for automation. We present a novel unsupervised semi-para…
A Multimodal Human Protein Embeddings Database: DeepDrug Protein Embeddings Bank (DPEB)
Md Saiful Islam Sajol, Magesh Rajasekaran, Hayden Gemeinhardt +3
Computationally predicting protein-protein interactions (PPIs) is challenging due to the lack of integrated, multimodal protein representations. DPEB is a curated collection of 22,…
Semi-Supervised Deep Domain Adaptation for Predicting Solar Power Across Different Locations
Md Shazid Islam, A S M Jahid Hasan, Md Saydur Rahman +1
Accurate solar generation prediction is essential for proper estimation of renewable energy resources across diverse geographic locations. However, geographical and weather feature…