DBN网络的深度确定方法  

Calculation for depth of deep belief network

作　　者：潘广源[1] 柴伟[1] 乔俊飞[1] 

机构地区：[1]北京工业大学电子信息与控制工程学院,北京100124

出　　处：《控制与决策》2015年第2期256-260,共5页Control and Decision

基　　金：国家杰出青年科学基金项目(61225016);国家自然科学基金重点项目(61034008);北京市自然科学基金青年基金项目(4144067)

摘　　要：针对DBN网络隐含层层数难以选择的问题,首先从数学生物学角度分析了随机初始化的梯度下降法导致网络训练失败的原因,并进行验证,证明了RBM重构误差与网络能量的正相关定理;然后根据隐含层和误差的关系,提出一种基于重构误差的网络深度判断方法,在训练过程中自组织地训练网络,使其能够以一种接近人类处理问题的方式解决AI问题.手写数字识别的实验表明,该方法能够有效提高运算效率,降低运算成本.In order to calculate the depth of deep belief network（DBN） in its applications, the reason of failure in training by using random initialization in gradient-based is analyzed in both math and biology, and then verified by the test. The theorem that the reconstruction error of restricted boltzmann machine（RBM） is related to network’s energy function is proved. After that, a method to calculate the depth by using restructure error in RBM is proposed based on the relationship between hidden layers and errors. DBN approaches human-level performance in AI tasks after the self-training. The experiment of hand writing digital recognition shows that the proposed method can improve the efficiency and lower the cost.

关 键 词：深度信念网络 网络深度 无监督学习 数字识别 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]