Machine Learning
290 views
Batch Normalization
Quick Definition
Normalizing layer inputs to stabilize and speed up training
Full Definition
A technique normalizing layer inputs during training to stabilize and accelerate neural network convergence.
Examples
faster training, reduced covariate shift, higher learning rates
Related Terms
deep-learning
neural-network
gradient-descent
More Machine Learning Terms
Feature Engineering
Creating and transforming input variables to improve performance
Lasso Regression
Regularized regression using L1 penalty for feature selection
K-Nearest Neighbors
Classifying based on majority class of k nearest neighbors
K-Means
Partitioning data into k clusters by updating centroids
Learning Rate
Hyperparameter controlling gradient descent step size
Active Learning
Algorithm selecting most informative data points for labeling