Loading
Self-supervised pretraining teaches a model from unlabelled data by hiding part of each example and asking it to predict the hidden part, so no expert labels are needed.
Self-supervised learning trains a model on a task where the data itself provides the supervisory signal rather than external labels (Wikipedia); masking, contrastive objectives and next-token prediction are the common forms. It matters in cancer because unlabelled slides, cells and expression profiles exist by the million while outcome labels exist by the hundred. Whether pretraining beats training from scratch on the labelled task is an empirical question and, for bulk expression at TCGA scale, several groups have reported that it does not.
Shares Transfer learning and the low-label regime, Foundation model, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Masked autoencoders and masked gene modelling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Masked autoencoders and masked gene modelling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Contrastive learning (InfoNCE), Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Foundation model, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Transfer learning and the low-label regime, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Masked autoencoders and masked gene modelling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Contrastive learning (InfoNCE), Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.