Visualizing neural networks for pattern recognition

Victor Jacobson, J. Jenny Li, Kevin Tapia, Patricia Morreale

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Understanding how a machine learns is a pressing topic as machine learning becomes more complex enabled by more powerful computers. This paper presents a visualization of neural networks to make them trackable during the operation of learning for pattern recognition, as well as testing for patterns. Specifically, our implementation includes fully connected neural networks, convolutional neural networks, and networks with memories. This will help us understand the insight of neural networks for pattern recognition to ensure full human control of the machines and to eliminate public‘s concern of recent leap in AI and machine learning. The visualization also helps to measure and identify performance bottleneck for future improvement.

Original languageEnglish
Title of host publicationProceedings of 2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018
PublisherAssociation for Computing Machinery
Pages18-22
Number of pages5
ISBN (Electronic)9781450364829
DOIs
StatePublished - 15 Aug 2018
Event2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018 - Union, United States
Duration: 15 Aug 201817 Aug 2018

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2018 International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2018
Country/TerritoryUnited States
CityUnion
Period15/08/1817/08/18

Keywords

  • CNN
  • Neural networks
  • Pattern recognition
  • RNN.

Fingerprint

Dive into the research topics of 'Visualizing neural networks for pattern recognition'. Together they form a unique fingerprint.

Cite this