How Neural Networks (NN) Can (Hopefully) Learn Faster by Taking into Account Known Constraints

Chitta Baral, Martine Ceberio, Vladik Kreinovich

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Neural networks are a very successful machine learning technique. At present, deep (multi-layer) neural networks are the most successful among the known machine learning techniques. However, they still have some limitations, One of their main limitations is that their learning process still too slow. The major reason why learning in neural networks is slow is that neural networks are currently unable to take prior knowledge into account. As a result, they simply ignore this knowledge and simulate learning “from scratch”. In this paper, we show how neural networks can take prior knowledge into account and thus, hopefully, learn faster.

Original languageEnglish (US)
Title of host publicationStudies in Systems, Decision and Control
PublisherSpringer
Pages15-20
Number of pages6
DOIs
StatePublished - 2020

Publication series

NameStudies in Systems, Decision and Control
Volume276
ISSN (Print)2198-4182
ISSN (Electronic)2198-4190

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Control and Systems Engineering
  • Automotive Engineering
  • Social Sciences (miscellaneous)
  • Economics, Econometrics and Finance (miscellaneous)
  • Control and Optimization
  • Decision Sciences (miscellaneous)

Fingerprint Dive into the research topics of 'How Neural Networks (NN) Can (Hopefully) Learn Faster by Taking into Account Known Constraints'. Together they form a unique fingerprint.

Cite this