Deep ConvNet: Non-Random Weight Initialization for Repeatable Determinism, Examined with FSGM

Deep ConvNet: Non-Random Weight Initialization for Repeatable Determinism, Examined with FSGM

A repeatable and deterministic non-random weight initialization method in convolutional layers of neural networks examined with the Fast Gradient Sign Method (FSGM). Using the FSGM approach as a technique to measure the initialization effect with controlled distortions in transferred learning, varyi...

Full description

Bibliographic Details
Main Authors: Richard N. M. Rudd-Orthner, Lyudmila Mihaylova
Format: Article
Language:English
Published: MDPI AG 2021-07-01
Series:Sensors
Subjects:
repeatable determinism
weight initialization
convolutional layers
adversarial perturbation attack
FSGM
transferred learning
Online Access:https://www.mdpi.com/1424-8220/21/14/4772

Internet

https://www.mdpi.com/1424-8220/21/14/4772

Similar Items