To compress or not to compress—self-supervised learning and information theory: A review
Deep neural networks excel in supervised learning tasks but are constrained by the need for
extensive labeled data. Self-supervised learning emerges as a promising alternative …
extensive labeled data. Self-supervised learning emerges as a promising alternative …
Firerisk: A remote sensing dataset for fire risk assessment with benchmarks using supervised and self-supervised learning
In recent decades, wildfires have caused tremendous property losses, fatalities, and
extensive damage to forest ecosystems. Inspired by the abundance of publicly available …
extensive damage to forest ecosystems. Inspired by the abundance of publicly available …
Reverse engineering self-supervised learning
Understanding the learned representation and underlying mechanisms of Self-Supervised
Learning (SSL) often poses a challenge. In this paper, we 'reverse engineer'SSL, conducting …
Learning (SSL) often poses a challenge. In this paper, we 'reverse engineer'SSL, conducting …
Transfer learning for chemically accurate interatomic neural network potentials
Develo** machine learning-based interatomic potentials from ab initio electronic structure
methods remains a challenging task for computational chemistry and materials science. This …
methods remains a challenging task for computational chemistry and materials science. This …
An information theory perspective on variance-invariance-covariance regularization
Abstract Variance-Invariance-Covariance Regularization (VICReg) is a self-supervised
learning (SSL) method that has shown promising results on a variety of tasks. However, the …
learning (SSL) method that has shown promising results on a variety of tasks. However, the …
Uncertainty Quantification in Machine Learning for Biosignal Applications--A Review
Uncertainty Quantification (UQ) has gained traction in an attempt to fix the black-box nature
of Deep Learning. Specifically (medical) biosignals such as electroencephalography (EEG) …
of Deep Learning. Specifically (medical) biosignals such as electroencephalography (EEG) …
Beyond deep ensembles: A large-scale evaluation of bayesian deep learning under distribution shift
Bayesian deep learning (BDL) is a promising approach to achieve well-calibrated
predictions on distribution-shifted data. Nevertheless, there exists no large-scale survey that …
predictions on distribution-shifted data. Nevertheless, there exists no large-scale survey that …