Neocognitron capable of incremental learning

Authors:
Kunihiko Fukushima
Affiliations:
School of Media Science, Tokyo University of Technology, 1404-1 Katakura Hachioji, Tokyo 192-0982, Japan
Venue:
Neural Networks
Year:
2004

Citing 8
Cited 5

A resource-allocating network for function interpolation

Neural Computation
Gaussian ARTMAP: a neural network for fast incremental learning of noisy multidimensional maps

Neural Networks
A sequential learning scheme for function approximation using minimal radial basis function neural networks

Neural Computation
Pruning with replacement on limited resource allocating networks by f-projections

Neural Computation
Learn++: an incremental learning algorithm for supervised neuralnetworks

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Incremental learning methods with retrieving of interfered patterns

IEEE Transactions on Neural Networks
Heuristic pattern correction scheme using adaptively trained generalized regression neural networks

IEEE Transactions on Neural Networks
A fuzzy ARTMAP nonparametric probability estimator for nonstationary pattern recognition problems

IEEE Transactions on Neural Networks

Recent Advances in the Neocognitron

Neural Information Processing
Coding of objects in low-level visual cortical areas

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Learning location invariance for object recognition and localization

BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence
Pixel-based machine learning in medical imaging

Journal of Biomedical Imaging - Special issue on Machine Learning in Medical Imaging
Artificial vision by multi-layered neural networks: Neocognitron and its advances

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new neocognitron that accepts incremental learning, without giving a severe damage to old memories or reducing learning speed. The new neocognitron uses a competitive learning, and the learning of all stages of the hierarchical network progresses simultaneously.To increase the learning speed, conventional neocognitrons of recent versions sacrificed the ability of incremental learning, and used a technique of sequential construction of layers, by which the learning of a layer started after the learning of the preceding layers had completely finished. If the learning speed is simply set high for the conventional neocognitron, simultaneous construction of layers produces many garbage cells, which become always silent after having finished the learning. The proposed neocognitron with a new learning method can prevent the generation of such garbage cells even with a high learning speed, allowing incremental learning.