ScholarGate
Assistent

Compara mètodes

Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.

Entrenament adversarial×Generative Adversarial Network×
CampAprenentatge profundAprenentatge profund
FamíliaMachine learningMachine learning
Any d'origen20182014
Autor originalAleksander Madry et al.Goodfellow, I. et al.
TipusRobust optimization training procedureGenerative deep learning (adversarial two-network game)
Font seminalMadry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. International Conference on Learning Representations (ICLR). link ↗Goodfellow, I. et al. (2014). Generative Adversarial Nets. NeurIPS. link ↗
ÀliesMin-Max Robust Training, PGD Adversarial Training, Robust Empirical Risk Minimization, Hasımsal EğitimÜretici Çekişmeli Ağ (GAN), GAN, generative adversarial nets, adversarial network
Relacionats34
ResumAdversarial 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.A Generative Adversarial Network (GAN), introduced by Ian Goodfellow and colleagues in 2014, produces realistic synthetic data through the competition of two neural networks — a generator and a discriminator. It is widely used for image synthesis, data augmentation, and distribution estimation.
ScholarGateConjunt de dades
  1. v1
  2. 1 Fonts
  3. PUBLISHED
  1. v1
  2. 2 Fonts
  3. PUBLISHED

Ves a la cerca Baixa les diapositives

ScholarGateCompara mètodes: Adversarial Training · Generative Adversarial Network. Recuperat el 2026-06-15 de https://scholargate.app/ca/compare