Transfer learning for Latin and Chinese characters with deep neural networks

Dan C. Ciresan, Ueli Meier, Jurgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

184 Scopus citations

Abstract

We analyze transfer learning with Deep Neural Networks (DNN) on various character recognition tasks. DNN trained on digits are perfectly capable of recognizing uppercase letters with minimal retraining. They are on par with DNN fully trained on uppercase letters, but train much faster. DNN trained on Chinese characters easily recognize uppercase Latin letters. Learning Chinese characters is accelerated by first pretraining a DNN on a small subset of all classes and then continuing to train on all classes. Furthermore, pretrained nets consistently outperform randomly initialized nets on new tasks with few labeled data. © 2012 IEEE.
Original languageEnglish (US)
Title of host publicationProceedings of the International Joint Conference on Neural Networks
DOIs
StatePublished - Aug 22 2012
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14

Fingerprint

Dive into the research topics of 'Transfer learning for Latin and Chinese characters with deep neural networks'. Together they form a unique fingerprint.

Cite this