1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Investigating Generalization In Neural Networks Under Optimally Evolved Training Perturbations

Investigating Generalization In Neural Networks Under Optimally Evolved Training Perturbations

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can cause drastic overfitting. We propose an evolutionary algorithm to search fo

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Investigating Generalization In Neural Networks Under Optimally Evolved Training Perturbations

00:15:05

0 views

In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can cause drastic overfitting. We propose an evolutionary algorithm to search fo