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

[31] A conjugate neural representation of visual objects in three dimensions
Zhang, KC
Sejnowski, TJ
PROCEEDINGS OF THE 4TH JOINT SYMPOSIUM ON NEURAL COMPUTATION, VOL 7, 1997, : 249 - 256
[32] On the optimal partitioning of data with K-means, growing K-means, neural gas, and growing neural gas
Daszykowski, M
Walczak, B
Massart, DL
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2002, 42 (06): : 1378 - 1389
[33] Representation Topology Divergence: a Method for Comparing Neural Network Representations
Barannikov, Serguei
Trofimov, Ilya
Balabin, Nikita
Burnaev, Evgeny
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[34] Evolving the topology and the weights of neural networks using a dual representation
Pujol, JCF
Poli, R
APPLIED INTELLIGENCE, 1998, 8 (01) : 73 - 84
[35] Evolving the Topology and the Weights of Neural Networks Using a Dual Representation
João Carlos Figueira Pujol
Riccardo Poli
Applied Intelligence, 1998, 8 : 73 - 84
[36] Image compression using growing neural gas
Garcia-Rodriguez, J.
Florez-Revuelta, F.
Garcia-Chamizo, J. M.
2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 366 - 370
[37] Mapping the growing neural gas to situation calculus
Vogiatzis, D
Stafylopatis, A
ARTIFICIAL NEURAL NETWORKS - ICANN 2002, 2002, 2415 : 957 - 962
[38] Comparing neural networks: A benchmark on growing neural gas, growing cell structures, and fuzzy ARTMAP
Heinke, D
Hamker, FH
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (06): : 1279 - 1291
[39] Growing Neural Gas with Correntropy Induced Metric
Masuyama, Naoki
Loo, Chu Kiong
PROCEEDINGS OF 2016 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2016,
[40] Locally weighted interpolating growing neural gas
Flentge, Felix
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2006, 17 (06): : 1382 - 1393

← 1 2 3 4 5 →