Exploring Neural Network Hidden Layer Activity Using Vector Fields

Deep Neural Networks are known for impressive results in a wide range of applications, being responsible for many advances in technology over the past few years. However, debugging and understanding neural networks models’ inner workings is a complex task, as there are several parameters and variabl...

Full description

Bibliographic Details

Published in:	Information
Main Authors:	Gabriel D. Cantareira, Elham Etemad, Fernando V. Paulovich
Format:	Article
Language:	English
Published:	MDPI AG 2020-08-01
Subjects:	explainable machine learning neural network visualization dimensionality reduction
Online Access:	https://www.mdpi.com/2078-2489/11/9/426