Machine Learning
27 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
Loss Function
Math function measuring prediction vs actual value difference
ARIMA
Statistical model for time series analysis and forecasting
Gradient Boosting
Sequential ensemble method correcting previous model errors
Online Learning
Updating models incrementally as new data arrives
Gradient Descent
Optimization algorithm minimizing loss by steepest descent
Linear Regression
Modeling variable relationships by fitting a linear equation