High-frequency Component Helps Explain the Generalization of Convolutional Neural Networks | AISC
Subscribers:
20,300
Published on ● Video Link: https://www.youtube.com/watch?v=Njpip9-_Xug
For slides and more information on the paper, visit https://ai.science/e/high-frequency-component-helps-explain-the-generalization-of-convolutional-neural-networks--HVAyCyALo5x54CyWLPXv
Speaker: Haohan Wang; Host: Ali El-Sharif
Motivation:
Computer Vision implementations based on Convolutional Neural Networks (CNN) have been reported to be unstable and vulnerable to adversarial attacks that are not visible to humans. This work investigates frequency spectrum of image data to explain the generalization behaviors convolutional neural networks (CNN).
Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE
Tags:
machine learning
deep learning
al interpretability
ai explainability
machine learning research