Machine Learning
145 views
Gradient Descent
Quick Definition
Optimization algorithm minimizing loss by steepest descent
Full Definition
An optimization algorithm minimizing a loss function by moving in the direction of steepest descent.
Examples
neural network training, parameter optimization, loss minimization
Related Terms
backpropagation
learning-rate
optimization
More Machine Learning Terms
ROC Curve
Plot showing classifier performance across thresholds
Naive Bayes
Probabilistic classifier using Bayes theorem with independence
A/B Testing
Statistical method comparing two versions for performance
Hyperparameter Tuning
Finding optimal configuration values before training
LightGBM
Fast gradient boosting framework using histogram splitting
Batch Normalization
Normalizing layer inputs to stabilize and speed up training