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 language||English (US)|
|Title of host publication||Proceedings of the International Joint Conference on Neural Networks|
|State||Published - Aug 22 2012|