Representational Learning with Extreme Learning Machine for Big Data Liyanaarachchi
Representational Learning with Extreme Learning Machine for Big Data Liyanaarachchi
复制标题
DOI：
--
复制
发表时间：
--
期刊：
影响因子：
--
通讯作者：
L. C. Kasun;Hongming Zhou;G. Huang;C. Vong
中科院分区：
文献类型：
--
作者：
L. C. Kasun;Hongming Zhou;G. Huang;C. Vong
受限玻尔兹曼机（RBM）和自动编码器，学习有意义地表示数据集中的特征，并用作创建深度网络的基本构建块。本文介绍了基于极限学习机的自动编码器（ELM-AE），该编码器利用奇异值学习特征表示，并将其作为多层极限学习机（ML-ELM）的基本构件。ML-ELM的性能优于基于自动编码器的深度网络和深度信念网络（DBN），而在MNIST数据集上与深度玻尔兹曼机（DBM）相当。然而，MLELM比任何先进的深度网络都要快得多。
Restricted Boltzmann Machines (RBM) and auto encoders, learns to represent features in a dataset meaningfully and used as the basic building blocks to create deep networks. This paper introduces Extreme Learning Machine based Auto Encoder (ELM-AE), which learns feature representations using singular values and is used as the basic building block for Multi Layer Extreme Learning Machine (ML-ELM). ML-ELM performance is better than auto encoders based deep networks and Deep Belief Networks (DBN), while in par with Deep Boltzmann Machines (DBM) for MNIST dataset. However MLELM is significantly faster than any state−of−the−art deep networks.