A self-organising network that grows when required

Authors:
Stephen Marsland;Jonathan Shapiro;Ulrich Nehmzow
Affiliations:
Division of Imaging Science and Biomedical Engineering, Stopford Building, University of Manchester, Oxford Road, Manchester M13 9PT, UK;Department of Computer Science, University of Manchester, Oxford Road, Manchester M13 9PL, UK;Department of Computer Science, University of Essex, Colchester CO4 3SQ, UK
Venue:
Neural Networks - New developments in self-organizing maps
Year:
2002

Citing 13
Cited 59

The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network

Computer
Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Designing a layered network for context sensitive pattern classification

Neural Networks
The cascade-correlation learning architecture

Advances in neural information processing systems 2
Topology representing networks

Neural Networks
A probabilistic resource allocating network for novelty detection

Neural Computation
Growing cell structures—a self-organizing network for unsupervised and supervised learning

Neural Networks
Dynamic cell structure learns perfectly topology preserving map

Neural Computation
A unifying objective function for topographic mappings

Neural Computation
The Probabilistic Growing Cell Structures Algorithm

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
A Self-Organizing Network that Can Follow Non-stationary Distributions

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Constructing maps for mobile robot navigation based on ultrasonic range data

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Topology preservation in self-organizing feature maps: exact definition and measurement

IEEE Transactions on Neural Networks

A Dynamic Adaptive Self-Organising Hybrid Model for Text Clustering

ICDM '03 Proceedings of the Third IEEE International Conference on Data Mining
An Architecture for Behavior-Based Reinforcement Learning

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Early lexical development in a self-organizing neural network

Neural Networks - 2004 Special issue: New developments in self-organizing systems
Online data visualization using the neural gas network

Neural Networks - 2006 Special issue: Advances in self-organizing maps--WSOM'05
Color reduction and estimation of the number of dominant colors by using a self-growing and self-organized neural gas

Engineering Applications of Artificial Intelligence
A self-organizing neural network for detecting novelties

Proceedings of the 2007 ACM symposium on Applied computing
Real-time Automated Visual Inspection using Mobile Robots

Journal of Intelligent and Robotic Systems
Letters: Selective attention-based novelty scene detection in dynamic environments

Neurocomputing
Visual novelty detection with automatic scale selection

Robotics and Autonomous Systems
Evolving a dynamic predictive coding mechanism for novelty detection

Knowledge-Based Systems
Following non-stationary distributions by controlling the vector quantization accuracy of a growing neural gas network

Neurocomputing
Autonomous virtual mobile robot for three-dimensional medical image exploration: Application to micro-CT cochlear images

Artificial Intelligence in Medicine
Intentional motion on-line learning and prediction

Machine Vision and Applications
A Multi-scale Dynamically Growing Hierarchical Self-organizing Map for Brain MRI Image Segmentation

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Incremental Knowledge Representation Based on Visual Selective Attention

Neural Information Processing
RLTE: Reinforcement Learning for Traffic-Engineering

AIMS '08 Proceedings of the 2nd international conference on Autonomous Infrastructure, Management and Security: Resilient Networks and Services
Dynamic Growing Self-organizing Neural Network for Clustering

ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
Structure Automatic Change in Neural Network

ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
A constrained neural learning rule for eliminating the border effect in online self-organising maps

Connection Science
Top-Down Object Color Biased Attention Using Growing Fuzzy Topology ART

IDEAL '08 Proceedings of the 9th International Conference on Intelligent Data Engineering and Automated Learning
Novelty detection with application to data streams

Intelligent Data Analysis - Knowledge Discovery from Data Streams
Review article: Local adaptive receptive field self-organizing map for image color segmentation

Image and Vision Computing
Self-Organizing Maps versus Growing Neural Gas in a Robotic Application

IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Exploiting data topology in visualization and clustering of self-organizing maps

IEEE Transactions on Neural Networks
Associative memory for online learning in noisy environments using self-organizing incremental neural network

IEEE Transactions on Neural Networks
A growing self-organizing network for reconstructing curves and surfaces

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Growing self-organizing surface map: Learning a surface topology from a point cloud

Neural Computation
Office-mate: selective attention and incremental object perception

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Content-based image retrieval using growing hierarchical self-organizing quadtree map

Pattern Recognition
A novel approach for distributed application scheduling based on prediction of communication events

Future Generation Computer Systems
Deformable radial basis functions

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Evolving tree algorithm modifications

IDEAL'07 Proceedings of the 8th international conference on Intelligent data engineering and automated learning
A knowledge synthesizing approach for classification of visual information

VISUAL'07 Proceedings of the 9th international conference on Advances in visual information systems
Learning Affordances of Consummatory Behaviors: Motivation-Driven Adaptive Perception

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Continuous visual codebooks with a limited branching tree growing neural gas

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Letters: Growing fuzzy topology adaptive resonance theory models with a push-pull learning algorithm

Neurocomputing
Pseudo-network growing for gradual interpretation of input patterns

ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II
Statistical estimation and modified learning vector quantization based flexible fuzzy neural networks with applications

ICCOMP'06 Proceedings of the 10th WSEAS international conference on Computers
Fully automatic shape modelling using growing cell neural networks

MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Unsupervised modeling of partially observable environments

ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part I
Frameworks for multivariate m-mediods based modeling and classification in Euclidean and general feature spaces

Pattern Recognition
Adaptive object recognition model using incremental feature representation and hierarchical classification

Neural Networks
Growing neural gas for vision tasks with time restrictions

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Data clustering with a neuro-immune network

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
A dynamic allocation method of basis functions in reinforcement learning

AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
Combining self-organizing maps with mixtures of experts: application to an actor-critic model of reinforcement learning in the basal ganglia

SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior
Measuring GNG topology preservation in computer vision applications

KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
IPSOM: a self-organizing map spatial model of how humans complete interlocking puzzles

AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Integration of growing self-organizing map and continuous genetic algorithm for grading lithium-ion battery cells

Applied Soft Computing
2012 Special Issue: Autonomous Growing Neural Gas for applications with time constraint: Optimal parameter estimation

Neural Networks
2013 Special Issue: Self-organizing adaptive map: Autonomous learning of curves and surfaces from point samples

Neural Networks
Novelty detection algorithm for data streams multi-class problems

Proceedings of the 28th Annual ACM Symposium on Applied Computing
Improving time series modeling by decomposing and analyzing stochastic and deterministic influences

Signal Processing
Online behavior change detection in computer games

Expert Systems with Applications: An International Journal
Self-organizing maps with a time-varying structure

ACM Computing Surveys (CSUR)
Top-down attention based on object representation and incremental memory for knowledge building and inference

Neural Networks
Review: A review of novelty detection

Signal Processing
Data stream dynamic clustering supported by Markov chain isomorphisms

Intelligent Data Analysis
Mimicking human neuronal pathways in silico: an emergent model on the effective connectivity

Journal of Computational Neuroscience

Quantified Score

Hi-index	0.00

Visualization

Abstract

The ability to grow extra nodes is a potentially useful facility for a self-organising neural network. A network that can add nodes into its map space can approximate the input space more accurately, and often more parsimoniously, than a network with predefined structure and size, such as the Self-Organising Map. In addition, a growing network can deal with dynamic input distributions. Most of the growing networks that have been proposed in the literature add new nodes to support the node that has accumulated the highest error during previous iterations or to support topological structures. This usually means that new nodes are added only when the number of iterations is an integer multiple of some pre-defined constant, λ.This paper suggests a way in which the learning algorithm can add nodes whenever the network in its current state does not sufficiently match the input. In this way the network grows very quickly when new data is presented, but stops growing once the network has matched the data. This is particularly important when we consider dynamic data sets, where the distribution of inputs can change to a new regime after some time.We also demonstrate the preservation of neighbourhood relations in the data by the network. The new network is compared to an existing growing network, the Growing Neural Gas (GNG), on a artificial dataset, showing how the network deals with a change in input distribution after some time. Finally, the new network is applied to several novelty detection tasks and is compared with both the GNG and an unsupervised form of the Reduced Coulomb Energy network on a robotic inspection task and with a Support Vector Machine on two benchmark novelty detection tasks.