Linganisha mbinu

	Uongezaji Data	Mafunzo Dhidi ya Mashambulizi
Nyanja	Ujifunzaji wa Kina	Ujifunzaji wa Kina
Familia	Machine learning	Machine learning
Mwaka wa asili	2019	2018
Mwanzilishi	Connor Shorten & Taghi Khoshgoftaar	Aleksander Madry et al.
Aina	Regularization / data preprocessing technique	Robust optimization training procedure
Chanzo asilia	Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6, 60.	Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. International Conference on Learning Representations (ICLR).
Majina mbadala	Training Data Augmentation, Image Augmentation, Veri Artırma, Synthetic Data Augmentation	Min-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal Eğitim
Zinazohusiana	2	3
Muhtasari	Data augmentation is a family of techniques that artificially expands a training dataset by applying label-preserving transformations to existing samples. Originally systematized for image classification tasks, it is now applied broadly across vision, text, audio, and tabular domains. It emerged as a practical answer to the chronic scarcity of labeled data in supervised deep learning and remains a standard preprocessing step in modern neural network pipelines.	Adversarial Training is a robust optimization procedure for deep neural networks in which the model is trained not on clean data alone but on worst-case perturbed inputs crafted during training. Formalized by Madry et al. (2018) as a min-max saddle-point problem, the method uses Projected Gradient Descent (PGD) to generate strong adversarial examples within a bounded Lp perturbation set before each gradient update, forcing the network to learn decision boundaries that are stable under such perturbations.