Login / Signup
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks.
Etai Littwin
Omid Saremi
Madhu Advani
Vimal Thilak
Preetum Nakkiran
Chen Huang
Joshua M. Susskind
Published in:
CoRR (2024)
Keyphrases
</>
feature vectors
machine learning
feature space
co occurrence
feature set
benchmark datasets
noisy data
data sets
neural network
computer vision
face recognition
feature extraction
image features
principal component analysis
structural information
noisy observations