Adaptive representation of objects topology deformations with growing neural gas

被引：0

作者：

Garcia-Rodriguez, Jose ^{[1
]}

Florez-Revuelta, Francisco ^{[1
]}

Garcia-Chamizo, Juan Manuel ^{[1
]}

机构：

[1] Univ Alicante, Dept Comp Technol, Apdo 99, E-03080 Alicante, Spain

来源：

COMPUTATIONAL AND AMBIENT INTELLIGENCE | 2007年 / 4507卷

关键词：

topology preservation; topology representation; self-organising neural networks; shape representation;

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：

Self-organising neural networks try to preserve the topology of an input space by means of their competitive learning. This capacity has been used, among others, for the representation of objects and their motion. In this work we use a kind of self-organising network, the Growing Neural Gas, to represent deformations in objects along a sequence of images. As a result of an adaptive process the objects are represented by a topology representing graph that constitutes an induced Delaunay triangulation of their shapes. These maps adapt the changes in the objects topology without reset the learning process.

引用

页码：244 / +

页数：3

共 50 条

[1] Analysis of the topology preservation of accelerated growing neural gas in the representation of bidimensional objects
Revuelta, FF
Chamizo, JMG
Rodríguez, JG
Sáez, AH
CURRENT TOPICS IN ARTIFICIAL INTELLIGENCE, 2004, 3040 : 167 - 176
[2] Mapping the dimensionality, density and topology of data:: The growing adaptive neural gas
Cselényi, Z
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2005, 78 (02) : 141 - 156
[3] Characterization and synthesis of objects using growing neural gas
García, J
Flórez, F
García, JM
Hernández, A
COMPUTATIONAL INTELLIGENCE AND BIOINSPIRED SYSTEMS, PROCEEDINGS, 2005, 3512 : 630 - 636
[4] Adaptive acquisition of virtualized deformable objects with a neural gas network
Cretu, AM
Lang, J
Petriu, EM
2005 IEEE INTERNATIONAL WORKSHOP ON HAPTIC AUDIO VISUAL ENVIRONMENTS AND THEIR APPLICATIONS, 2005, : 165 - 170
[5] Neural gas sonification - Growing adaptive interfaces for interacting with data
Hermann, T
Ritter, H
EIGHTH INTERNATIONAL CONFERENCE ON INFORMATION VISUALISATION, PROCEEDINGS, 2004, : 871 - 878
[6] Fast Image Representation with GPU-Based Growing Neural Gas
Garcia-Rodriguez, Jose
Angelopoulou, Anastassia
Morell, Vicente
Orts, Sergio
Psarrou, Alexandra
Manuel Garcia-Chamizo, Juan
ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2011, PT II, 2011, 6692 : 58 - 65
[7] On the convergence of a growing topology neural algorithm
Drago, GP
Ridella, S
NEUROCOMPUTING, 1996, 12 (2-3) : 171 - 185
[8] On the convergence of a growing topology neural algorithm
Ist. per i Circuiti Elettronici, Via De Marini, 6, 16149 Genova, Italy
不详
NEUROCOMPUTING, 2-3 (171-185):
[9] Adaptive Function Approximation in Reinforcement Learning with an Interpolating Growing Neural Gas
Baumann, Michael
Buening, Hans Kleine
2012 12TH INTERNATIONAL CONFERENCE ON HYBRID INTELLIGENT SYSTEMS (HIS), 2012, : 512 - 517
[10] Roadmap Learning for Probabilistic Occupancy Maps With Topology-Informed Growing Neural Gas
Saroya, Manish
Best, Graeme
Hollinger, Geoffrey A.
IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (03): : 4805 - 4812

← 1 2 3 4 5 →