Machine Learning
25 views
Self-Supervised Learning
Quick Definition
Generating supervisory signals from unlabeled data for training
Full Definition
A ML approach where the model generates its own supervisory signal from unlabeled data.
Examples
BERT pre-training, contrastive learning, masked modeling
Related Terms
contrastive-learning
transfer-learning
More Machine Learning Terms
Autoencoder
Neural network learning compressed data representations
Batch Normalization
Normalizing layer inputs to stabilize and speed up training
Ridge Regression
Regularized regression using L2 penalty to prevent overfitting
A/B Testing
Statistical method comparing two versions for performance
Feature Selection
Identifying the most relevant features for model training
Clustering
Grouping similar data points based on feature similarity