Presentation Information
[1P-491]Does the optimal structure of Vision Transformer (ViT) demonstrate a universal scaling law in accordance with the scale of the training data?
*Rui Yamamoto1, Keiji Miura1 (1. Kwansei Gakuin University)
Keywords:
deep learning,image learning,neural network,diffusion models
Password required to view
Abstract password authentication.
A password is required to view the full text of the abstract. Please enter the following password.
PW: Neuro2024
A password is required to view the full text of the abstract. Please enter the following password.
PW: Neuro2024