Building fast and compact convolutional neural networks for offline handwritten Chinese character recognition

作者：

Highlights：

• We propose a new method for building fast and compact CNN model for large scale handwritten Chinese character recognition (HCCR).

• We propose a new technique, namely Adaptive Drop-weight (ADW), for effectively pruning CNN parameters.

• We proposed the Global Supervised Low Rank Expansions (GSLRE) method for accelerating CNN model.

• Comparing with the state-of-the-art CNN method for HCCR, our approach is about 30-times faster yet 10-times smaller.

摘要

•We propose a new method for building fast and compact CNN model for large scale handwritten Chinese character recognition (HCCR).•We propose a new technique, namely Adaptive Drop-weight (ADW), for effectively pruning CNN parameters.•We proposed the Global Supervised Low Rank Expansions (GSLRE) method for accelerating CNN model.•Comparing with the state-of-the-art CNN method for HCCR, our approach is about 30-times faster yet 10-times smaller.

论文关键词：Convolutional neural network,Handwritten Chinese character recognition,CNN acceleration,CNN compression

论文评审过程：Received 16 February 2017, Revised 31 May 2017, Accepted 26 June 2017, Available online 1 July 2017, Version of Record 7 July 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.06.032