Login / Signup
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks.
Huishuai Zhang
Da Yu
Yiping Lu
Di He
Published in:
CoRR (2022)
Keyphrases
</>
linearly separable
neural network
linear separability
input space
linear classifiers
hyperplane
high dimensional feature space
back propagation
decision boundary
feature space
pattern recognition
convex hull
data points
infinite dimensional
support vector machine
training samples
kernel function
euclidean space