A biologically motivated visual memory architecture for online learning of objects

Authors:
Stephan Kirstein;Heiko Wersing;Edgar Körner
Affiliations:
Honda Research Institute Europe GmbH, Carl-Legien-Str. 30, 63073 Offenbach am Main, Germany;Honda Research Institute Europe GmbH, Carl-Legien-Str. 30, 63073 Offenbach am Main, Germany;Honda Research Institute Europe GmbH, Carl-Legien-Str. 30, 63073 Offenbach am Main, Germany
Venue:
Neural Networks
Year:
2008

Citing 17
Cited 8

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

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

Neural Networks
Adaptive resonance theory (ART)

The handbook of brain theory and neural networks
A model of computation in neocortical architecture

Neural Networks - Special issue on organisation of computation in brain-like systems
Recognition without Correspondence using MultidimensionalReceptive Field Histograms

International Journal of Computer Vision
Life-long learning cell structures —continuously learning without catastrophic interference

Neural Networks
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Geometric Hashing: An Overview

IEEE Computational Science & Engineering
Tracing Patterns and Attention: Humanoid Robot Cognition

IEEE Intelligent Systems
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
Entropie als Maß des lokalen Informationsgehalts in Bildern zur Realisierung einer Aufmerksamkeitssteuerung

Mustererkennung 1996, 18. DAGM-Symposium
Learning optimized features for hierarchical models of invariant object recognition

Neural Computation
Incremental Online Learning in High Dimensions

Neural Computation
A Model of Invariant Object Recognition in the Visual System: Learning Rules, Activation Functions, Lateral Inhibition, and Information-Based Performance Measures

Neural Computation
An incremental network for on-line unsupervised classification and topology learning

Neural Networks
A biologically motivated system for unconstrained online learning of visual objects

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II

Incremental Figure-Ground Segmentation Using Localized Adaptive Metrics in LVQ

WSOM '09 Proceedings of the 7th International Workshop on Advances in Self-Organizing Maps
A vector quantization approach for life-long learning of categories

ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
An integrated system for incremental learning of multiple visual categories

ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Hand gesture recognition based on online PCA with adaptive subspace

MUSP'10 Proceedings of the 10th WSEAS international conference on Multimedia systems & signal processing
Online PCA with adaptive subspace method for real-time hand gesture learning and recognition

WSEAS Transactions on Computers
A perceptual memory system for affordance learning in humanoid robots

ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
Invariant object recognition and pose estimation with slow feature analysis

Neural Computation
A life-long learning vector quantization approach for interactive learning of multiple categories

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and incremental learning for the task of appearance-based object recognition of many complex-shaped objects. We propose some modifications of learning vector quantization algorithms that are especially adapted to the task of incremental learning and capable of dealing with the stability-plasticity dilemma of such learning algorithms. Our technical implementation of the neural architecture is capable of online learning of 50 objects within less than three hours.