BriefGPT.xyz
May, 2023
FICNN:深度卷积神经网络解释框架
FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks
HTML
PDF
Hamed Behzadi-Khormouji, José Oramas
TL;DR
本文提出了一种卷积神经网络模型解释框架,指出了模型解释和解释任务的差异,定义了用于表征解释方法的六个因素,并讨论了现有解释方法和评估协议对它们的验证,以及提出了可能出现的研究问题。
Abstract
With the continue development of
convolutional neural networks
(CNNs), there is a growing concern regarding representations that they encode internally. Analyzing these internal representations is referred to as
model i
→