The generation of synthetic data can be used for anonymization, regularization,
oversampling, semi-supervised learning, self-supervised learning, and several other tasks …

When we execute the typical fine-tuning paradigm on continuously sequential tasks, the
model will suffer from the catastrophic forgetting problem (ie, the model tends to adjust old …

Con2Mix (Contrastive Double Mixup) is a new semi-supervised learning methodology that
innovates a triplet mixup data augmentation approach for finding code vulnerabilities in …

Industrial control systems (ICSs) are getting integrated into cyber-physical systems (CPSs)
for a smarter and more energy-efficient society. As they organize the infrastructure of our …

The ConfliLPC framework introduces an innovative integration of Logits and Parameter
Calibration (LPC) with the ConfliBERT model, tailored specifically for the nuanced analysis …

The college admissions process is a very important step in every student's educational
journey. Students submit a comprehensive application which is judged holistically by an …

As cars evolve to be smarter than ever, they also become susceptible to attack. Malicious
entities can attempt to override automated functions by sending a series of attack signals to …

In the rapidly evolving field of machine learning, particularly in applications demanding
continual or sequential learning, the phenomenon of catastrophic forgetting poses a …

Abstract In remote sensing, Land Use/Land Cover (LULC) maps constitute important assets
for various applications, promoting environmental sustainability and good resource …

Proposal of self and semi-supervised learning for imbalanced classification of coronary heart
disease tabular data Page 1 Tecnología en Marcha. Vol. 37, special issue. August, 2024 IEEE …