Skip to main navigation Skip to search Skip to main content

Tri-self-taught learning of artificial neural networks

  • Feng Liu*
  • , Shuling Dai
  • *Corresponding author for this work
  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

We present a conceptually simple and general framework for self-taught learning, and this method can modify weights of neural networks when making prediction on samples according to the previous knowledge. The method called Tri-STNN. Based on Tri-training, it adds a Judge Network to make a higher accuracy of prediction. Tri-STNN is simple to be trained and the training datasets for Judge Network is easy to obtain. Moreover, Tri-STNN is capable of lots of tasks. We test Tri-STNN on the datasets of CIFAR-10, and the result shows that Tri-STNN can constantly keep self-taught learning and improve the generalization ability for new samples.

Original languageEnglish
Title of host publicationLecture Notes in Electrical Engineering
PublisherSpringer Verlag
Pages807-814
Number of pages8
DOIs
StatePublished - 2019

Publication series

NameLecture Notes in Electrical Engineering
Volume529
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Keywords

  • Artificial neural networks
  • Judge network
  • Lifelong- learning
  • Self-taught learning

Fingerprint

Dive into the research topics of 'Tri-self-taught learning of artificial neural networks'. Together they form a unique fingerprint.

Cite this