Noise Injection Techniques provides a comprehensive exploration of methods to make machine learning models more robust to real-world bad data. This repository explains and demonstrates Gaussian noise, dropout, mixup, masking, adversarial noise, and label smoothing, with intuitive explanations, theory, and practical code examples.
data-science machine-learning deep-learning tabular-data pytorch dropout neural-networks regularization data-augmentation data-quality noise-injection label-smoothing mixup ai-research gaussian-noise ml-engineering model-robustness adversarial-ml ml-theory ml-robustness
-
Updated
Nov 15, 2025