DBM-ELM深层网络模型  

The DBM-ELM deep network model

作　　者：刘世蕾[1] 崔晓明[1] 聂茹[1] 

机构地区：[1]中国矿业大学计算机科学与技术学院,徐州221116

出　　处：《南京大学学报（自然科学版）》2017年第3期497-505,共9页Journal of Nanjing University（Natural Science）

摘　　要：使用深层限制波尔兹曼机实现高维数据非线性降维,再结合极速学习机算法,提出了一种复合的DBMELM深层网络模型.该模型在复杂高维数据的分类问题上,能较好的将高维数据简化到低维空间,进而得到较好的分类效果,实现复杂函数的表示.最后在人脸和手写数字识别实验上得到了很好的证明.Deep learning is currently an extremely active research area in machine learning and pattern recognition society. Deep learning and Big Data are two hottest trends in rapidly growing digital world. Today, big data for the development of various industry has brought the huge opportunity and potential. On the other hand it has also brought unprecedented challenges. While big data has been defined in different ways, it is referred to the exponential growth and wide availability of digital data. It is difficult or even impossible to manage and analyze them using con- ventional software tools and technologies. It has gained huge successes in a broad area of applications such as speech recognition,computer vision and natural language processing. In the field of computer vision optical character recognition （OCR） concept was put forward in early 1920s. It is a representative in the field of pattern recognition research important topic. Recently,RBM（Restricted Boltzmann Machines） becomes increasingly popular because of its fast learning algorithm,Contrastive Divergence. For the theoretic perspective, the success of RBM has greatly en couraged the research about the stochastic approximation theory, energy-based models and unnormalized statistical models. For the application perspective, RBM has been successfully applied in various machine learning domains, such as classification, regression, dimension reduction, high-dimensional time series modeling, sparse over-complete representations,image transformations and collaborative filtering. In this article, we proposed a new compositional DBM-ELM network model based on deep Restricted Boltzmann machines which realize data nonlinear dimension reduction and Extreme Learning Machines algorithm. This model can simplify the high-dimensional data into low dimensional space better and then get a better classification effect to represent complicated functions. Finally the ex periments on face and handwritten digit recognition prove the superiority.

关 键 词：深层网络 深层限制波尔兹曼机 极速学习机 DBM-ELM 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]