Machine Learning
29 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
Dropout
Regularization randomly deactivating neurons during training
Machine Learning
AI subset where systems learn patterns from data
AdaBoost
Combining weak classifiers with adaptive sample weighting
Loss Function
Math function measuring prediction vs actual value difference
Self-Supervised Learning
Generating supervisory signals from unlabeled data for training
Markov Chain
Stochastic model where events depend only on previous state