Hierarchical deep neural network for multivariate regression
作者：
Highlights：
• Hierarchical deep neural network focuses on both deep and wide architectures.
• Decomposing a complicated regression problem into multiple subproblems to be solved.
• More powerful modeling capability and better learning convergence than DNN.
• Successful application for one regression problem (speech enhancement).
• Successful application for one classification problem (Chinese handwriting recognition).
摘要
Highlights•Hierarchical deep neural network focuses on both deep and wide architectures.•Decomposing a complicated regression problem into multiple subproblems to be solved.•More powerful modeling capability and better learning convergence than DNN.•Successful application for one regression problem (speech enhancement).•Successful application for one classification problem (Chinese handwriting recognition).
论文关键词：Divide and Conquer,Hierarchical Deep Neural Network,Multivariate Regression,Speech Enhancement,Handwritten Chinese Character Recognition
论文评审过程：Received 23 June 2015, Revised 12 April 2016, Accepted 1 October 2016, Available online 4 October 2016, Version of Record 15 October 2016.
论文官网地址：https://doi.org/10.1016/j.patcog.2016.10.003
