Machine Learning Research
Taming Spurious Correlations: New Technique Helps AI Avoid Classification Mistakes
When a neural network learns image labels, it may confuse a background item for the labeled object. New research avoids such mistakes.
Contrastive Learning
Machine Learning Research
Learning From Metadata: Descriptive Text Improves Performance for AI Image Classification Systems
Images in the wild may not come with labels, but they often include metadata. A new training method takes advantage of this information to improve contrastive learning.
Machine Learning Research
More Reliable Pretraining: Pretraining Method Helps AI Learn Useful Representations
Pretraining methods generate basic representations for later fine-tuning, but they’re prone to certain issues that can throw them off-kilter. New work proposes a solution.
Machine Learning Research
Learning From Words and Pictures: A deep learning method for medical x-rays with text
It’s expensive to pay doctors to label medical images, and the relative scarcity of high-quality training examples can make it hard for neural networks to learn features that make for accurate diagnoses.
Machine Learning Research
Unlabeled Brainwaves Spill Secrets: Deep learning helps doctors interpret EEGs.
For people with neurological disorders like epilepsy, attaching sensors to the scalp to measure electrical currents within the brain is benign. But interpreting the resulting electroencephalogram (EEG) graphs can give doctors a headache.
Machine Learning Research
RL and Feature Extraction Combined: CURL combines reinforcement with contrastive learning.
Which comes first, training a reinforcement learning model or extracting high-quality features? New work avoids this chicken-or-egg dilemma by doing both simultaneously.
Machine Learning Research
Self-Supervised Simplicity: Image classification with simple contrastive learning (SimCLR)
A simple linear classifier paired with a self-supervised feature extractor outperformed a supervised deep learning model on ImageNet, according to new research.