TY - GEN
T1 - Transfer learning for Latin and Chinese characters with deep neural networks
AU - Ciresan, Dan C.
AU - Meier, Ueli
AU - Schmidhuber, Jurgen
N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14
PY - 2012/8/22
Y1 - 2012/8/22
N2 - 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.
AB - 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.
UR - http://ieeexplore.ieee.org/document/6252544/
UR - http://www.scopus.com/inward/record.url?scp=84865094974&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2012.6252544
DO - 10.1109/IJCNN.2012.6252544
M3 - Conference contribution
SN - 9781467314909
BT - Proceedings of the International Joint Conference on Neural Networks
ER -