arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.03486cs.NEcs.CV
收藏

一种基于层生成算法的深度信念网络自适应学习方法

An Adaptive Learning Method of Deep Belief Network by Layer Generation Algorithm

Hiroshima City University(广岛市立大学);Prefectural University of Hiroshima(广岛县立大学)

Shin Kamada, Takumi Ichimura

摘要:

深度信念网络(DBN)具有一个深度架构,它使用预先训练的受限玻尔兹曼机(RBM)分层表示输入模式的多个特征。传统的RBM或DBN模型在学习阶段不能改变其网络结构。我们提出的自适应学习方法可以根据输入空间发现隐藏神经元的最佳数量以及权重和/或层。该模型是一种兼顾计算量和模型稳定性的重要方法。保持网络的稀疏结构是一个相当大的问题,因为需要从训练好的网络中提取显式知识。在我们之前的研究中,我们已经发展了RBM的自适应结构学习方法和学习遗忘方法的混合方法来训练RBM。在本文中,我们提出了DBN的自适应学习方法,可以在学习过程中确定最佳的层数。我们在一些基准数据集上评估了我们提出的模型。

英文摘要:

Deep Belief Network (DBN) has a deep architecture that represents multiple features of input patterns hierarchically with the pre-trained Restricted Boltzmann Machines (RBM). A traditional RBM or DBN model cannot change its network structure during the learning phase. Our proposed adaptive learning method can discover the optimal number of hidden neurons and weights and/or layers according to the input space. The model is an important method to take account of the computational cost and the model stability. The regularities to hold the sparse structure of network is considerable problem, since the extraction of explicit knowledge from the trained network should be required. In our previous research, we have developed the hybrid method of adaptive structural learning method of RBM and Learning Forgetting method to the trained RBM. In this paper, we propose the adaptive learning method of DBN that can determine the optimal number of layers during the learning. We evaluated our proposed model on some benchmark data sets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑