An Adaptive Statistical Neural Network Model

被引：0

作者：

Liu, Peilei ^{[1
,2
]}

Tang, Jintao ^{[1
]}

Liu, Haichi ^{[1
]}

Wang, Ting ^{[1
]}

机构：

[1] Natl Univ Def Technol, Coll Comp, Changsha 410073, Hunan, Peoples R China

[2] Acad Natl Def Informat, Dept Informat Resource Management, Wuhan 430010, Hubei, Peoples R China

来源：

2016 INTERNATIONAL CONFERENCE ON NETWORK AND INFORMATION SYSTEMS FOR COMPUTERS (ICNISC) | 2016年

基金：

中国国家自然科学基金;

关键词：

Neural network; statistical learning; incremental learning; clustering algorithm; LEARNING ALGORITHM;

D O I：

10.1109/ICNISC.2016.23

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Traditional back propagating algorithms of artificial neural network are supervised batch-learning algorithms. And they are faced with challenges from the huge number of real-time data in Internet. In this paper, we put forward an unsupervised incremental learning model. This is an adaptive statistical neural network model. It is built on the foundation of statistical theory rather than gradient descent search. Experiments on classical datasets demonstrate that the clustering algorithm of this model is comparable with traditional clustering algorithms such as K-means. Moreover, it can also execute supervised learning in theory.

引用

页码：242 / 246

页数：5

共 17 条

[1] ACKLEY DH, 1985, COGNITIVE SCI, V9, P147
[2] [Anonymous], PERCEPTRONS INTRO CO
[3] [Anonymous], 1986, FOUNDATIONS, DOI DOI 10.7551/MITPRESS/5236.001.0001
[4] [Anonymous], SIGKDD EXPLORATIONS
[5] [Anonymous], ARTIFICIAL NEURAL NE
[6] [Anonymous], WHY STAT SHOULD FART
[7] [Anonymous], 1987, THESIS
[8] Learning Deep Architectures for AI
Bengio, Yoshua
[J]. FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2009, 2 (01): : 1 - 127
[9] Grossberg S, 2012, NEURAL NETWORKS, V27, P1, DOI [10.1016/j.neunet.2012.09.017, 10.1016/j.neunet.2011.10.011]
[10] Hebb DO, 1949, ORG BEHAV NEUROPSYCH

← 1 2 →