Contextual Self-Supervised Learning: Machine learning adapts to new tasks without retraining
https://techxplore.com/news/2024-12-machine-tasks-retraining.html
"algorithm generate output labels automatically from raw data... relies on pre-defined data augmentations, learning from general representation adapted to different transformations paying attention to context, representing abstract task/ environment... incorporates world models, invariant/ equivariant based on task at hand... transformer module encodes context, triplets representing previous experiences with transformations... natural language processing, computer vision, bioinformatics, speech recognition"
Related:
Researcher develops 'SpeechSSM,' opening up possibilities for a 24-hour AI voice assistant
AI meets quantum: Machine learning advances estimation and control of quantum systems
Comments
Post a Comment