Abstract: In order to determine the number of hidden layers in continuous deep belief network (CDBN), a determination method for the depth of CDBN based on the reconstruction error is proposed. CDBN is composed of multiple continuous restricted Boltzmann machines (CRBM). By analyzing the relevance between the reconstruction error and the network energy, and setting the threshold of the reconstruction error, the decision mechanism for the depth is designed to realize self-organizing adjustment for the depth of CDBN. The experiments show that the determination method for the depth of CDBN based on the reconstruction error can determine the optimal depth of CDBN and improve the efficiency of decision depth for CDBN.

Key words: Continuous deep belief network, reconstruction error, depth of network, simulation experiments

摘要： 针对连续型深度信念网(Continuous Deep Belief Network，CDBN)隐含层层数难以确定的问题，提出一种基于重构误差的CDBN网络深度确定方法。多个连续型受限玻尔兹曼机(Continuous Restricted Boltzmann Machine，CRBM)叠加构成CDBN。通过分析CRBM的重构误差与CDBN网络能量的相关性, 设定重构误差阈值并设计网络深度决策机制，实现对CDBN隐含层层数进行自组织调整。仿真实验验证，基于重构误差的CDBN网络深度确定方法能够对CDBN的最优隐含层层数进行确定，有效提高了网络深度决策的效率。

关键词:

"> 连续型深度信念网, 重构误差, 网络深度, 仿真实验