Acta Scientiarum Naturalium Universitatis Pekinensis

Previous Articles     Next Articles

Modular-tree: A Self-architecture Neural Network Architecture

CHEN Ke1, YU Xiang1, CHI Huisheng1, YANG Liping2   

  1. 1National Lab of Machine Perception and Center for Information Science Peking University, Beijing, 100871, chen@; 2IBM China Research Lab, Beijing, 100085
  • Received:1995-09-21 Online:1996-01-20 Published:1996-01-20



  1. 1国家视觉听觉及信息处理实验室、北京大学信息科学中心,北京,100871;2,IBM中国实验室,北京,100085

Abstract: Presented a novel self-architecure modular neural network architecture, called modular-tree for supervised learning. In the architecture, any kind of feedforward neural networks can be employed as componenets and a modular neural network with the tree structure is generated automatically with a growing algorithm by partitioning input space recursively to avoid the problem of pre-determined structure. Due to the principle of divide-and-conquer used in the proposed architecture, the modular-tree can yield both a good performance and significantly fast training. The proposed architecture has been applied to several supervised learning tasks including both benchmark and real-world problems and achieved satisfactory results.

Key words: modular neural networks, self-architecture, supervised learning

摘要: 提出了一种新颖的具有自构筑能力的神经网络结构,称之为Modular-tree和两个相应的自构筑算法。在此结构中,任何现存的前馈神经网络均可以作为子网。对于一个给定的学习任务,利用提出的生成算法通过对输入空间递归地划分,自动生成一树状的模块神经网络,从而避免了网络结构预置问题。由于使用了“分治”原理,Modular-tree具有良好的性能及快速训练的能力。此结构已用于多个监督学习问题(包括:标准测试及现实世界问题)并取得令人满意的实验结果。

关键词: 模块神经网络, 自构筑, 监督学习

CLC Number: