Machine Learning
288 views
Data Augmentation
Quick Definition
Artificially increasing training data through modified copies
Full Definition
Artificially increasing training data size by creating modified copies of existing data.
Examples
image flipping, text paraphrasing, SMOTE for imbalanced data
Related Terms
overfitting
transfer-learning
deep-learning
More Machine Learning Terms
Multi-Task Learning
Training one model for multiple related tasks simultaneously
Bagging
Training models on random subsets and averaging predictions
Hidden Markov Model
Statistical model with hidden states and observable outputs
Backpropagation
Algorithm computing gradients for neural network weight updates
Feature Selection
Identifying the most relevant features for model training
Markov Chain
Stochastic model where events depend only on previous state