Explainability as a Method for Learning From Computers

Explainability as a Method for Learning From Computers

Humans have rich experience applying linear models and logical thinking, but only experts understand the behaviour of non-linear systems. However, the deep neural network (DNN) implementation of text non-linear systems outperforms optimal linear models. Therefore, the forward DNN (the pattern recogn...

Full description

Bibliographic Details
Main Authors: Martin Klimo, Jaroslav Kopcan, L'ubomir Kralik
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Explainability
feature extraction
neural networks
machine learning
pattern classification
Online Access:https://ieeexplore.ieee.org/document/10097489/

Internet

https://ieeexplore.ieee.org/document/10097489/

Similar Items