ManySpace
English Giriş yap Kayıt ol

Yapay ZekâÖnerilenAIML-SEC-002

Adversarial Training and Certified Robustness

Training on worst-case perturbations, and proving robustness within a radius.

Bu konunun henüz Türkçe çevirisi yok, bu yüzden İngilizce gösteriliyor.

Zorluk
3 / 5
Önem
4 / 5
Çalışma süresi
1–2 sa
Çalışma türü
Karma

Neden önemli

The learner can explain adversarial training as a min-max problem and describe the robustness-accuracy trade-off with the perturbation budget.

Bu konuya giden rota

Rota AIML-SEC-002
What Is a Model? Learning from Data Features and Targets Datasets and Splits Linear Regression I: Prediction and Residuals Sampling and Splits Train, Validation, and Test Errors Loss and Fitting: Squared Error Distribution Shift Offline Evaluation Objective Functions and Empirical Risk Robustness Evaluation Gradient Descent in Machine Learning Adversarial Examples Stochastic and Mini-batch Optimization Adversarial Training and Certified Robustness