An analysis of explainability methods for convolutional neural networks

Lynn Vonder Haar; Timothy Elvira; Omar Ochoa

doi:10.1016/j.engappai.2022.105606

ScienceGate Book Chapters

JOURNAL ARTICLE

An analysis of explainability methods for convolutional neural networks

Lynn Vonder Haar Timothy Elvira Omar Ochoa

Year: 2022 Journal: Engineering Applications of Artificial Intelligence Vol: 117 Pages: 105606-105606 Publisher: Elsevier BV

DOI: 10.1016/j.engappai.2022.105606

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Convolutional neural network Artificial intelligence Black box Reputation Machine learning Deep learning Meaning (existential) Image (mathematics)

Metrics

Cited By

15.66

FWCI (Field Weighted Citation Impact)

Refs

0.99

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Explainable Artificial Intelligence (XAI)

Physical Sciences → Computer Science → Artificial Intelligence

Adversarial Robustness in Machine Learning

Physical Sciences → Computer Science → Artificial Intelligence

Machine Learning and Data Classification

Physical Sciences → Computer Science → Artificial Intelligence

An analysis of explainability methods for convolutional neural networks

Metrics

Citation History

Topics

Related Documents

Explainability Methods for Graph Convolutional Neural Networks

Layer factor analysis in convolutional neural networks for explainability

Towards Explainability of non-Convolutional Neural Networks

Explainability of Convolutional Neural Networks for Dermatological Diagnosis

A concept-aware explainability method for convolutional neural networks