Unsupervised Learning Algorithm for Signal Separation

被引：0

作者：

Jacob, Theju ^{[1
]}

Snyder, Wesley ^{[1
]}

机构：

[1] North Carolina State Univ, Dept Elect & Comp Engn, Raleigh, NC 27695 USA

来源：

2014 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE FOR MULTIMEDIA, SIGNAL AND VISION PROCESSING (CIMSIVP) | 2014年

关键词：

SELF-ORGANIZATION; VISUAL-CORTEX; RECOGNITION; ORIENTATION;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a neural network capable of separating inputs in an unsupervised manner. Oja's rule and Self-Organizing map principles are used to construct the network. The network is tested using 1) straight lines 2) MNIST database. The results demonstrate that the network can operate as a general clustering algorithm, with neighboring neurons responding to geometrically similar inputs.

引用

页码：158 / 163

页数：6

共 24 条

[11]

KOHONEN T., 1977, ASS MEMORY SYSTEM TH

[12]

Kohonen T., 1997, SELF ORGANIZING MAPS

[13] Gradient-based learning applied to document recognition [J].

Lecun, Y ;

Bottou, L ;

Bengio, Y ;

Haffner, P .

PROCEEDINGS OF THE IEEE, 1998, 86 (11) :2278-2324

[14] SELF-ORGANIZATION OF ORIENTATION SENSITIVE CELLS IN STRIATE CORTEX [J].

MALSBURG, CV .

KYBERNETIK, 1973, 14 (02) :85-100

[15] THE ROLE OF CONSTRAINTS IN HEBBIAN LEARNING [J].

MILLER, KD ;

MACKAY, DJC .

NEURAL COMPUTATION, 1994, 6 (01) :100-126

[16]

Oja E., 1989, International Journal of Neural Systems, V1, P61, DOI 10.1142/S0129065789000475

[17] A SIMPLIFIED NEURON MODEL AS A PRINCIPAL COMPONENT ANALYZER [J].

OJA, E .

JOURNAL OF MATHEMATICAL BIOLOGY, 1982, 15 (03) :267-273

[18]

OJA E, 1991, ARTIFICIAL NEURAL NETWORKS, VOLS 1 AND 2, P385

[19]

OJA E, 1995, A26 HELS U TECHN LAB

[20]

RIESENHUBER M, 1999, NAT NEUROSCIENCE, V2

← 1 2 3 →