Machine Learning
301 views
Backpropagation
Quick Definition
Algorithm computing gradients for neural network weight updates
Full Definition
The fundamental algorithm for training neural networks by computing gradients using the chain rule.
Examples
neural network training, deep learning, optimization
Related Terms
gradient-descent
neural-network
loss-function
More Machine Learning Terms
Supervised Learning
Learning from labeled training data with input-output pairs
Ridge Regression
Regularized regression using L2 penalty to prevent overfitting
Boosting
Sequentially combining weak learners correcting previous errors
CatBoost
Gradient boosting library with native categorical feature support
Gradient Boosting
Sequential ensemble method correcting previous model errors
Precision Recall
Metrics measuring positive prediction quality and coverage