K
Kunihiko Fukushima
Researcher at Tokyo University of Technology
Publications - 40
Citations - 481
Kunihiko Fukushima is an academic researcher from Tokyo University of Technology. The author has contributed to research in topics: Neocognitron & Artificial neural network. The author has an hindex of 10, co-authored 40 publications receiving 444 citations. Previous affiliations of Kunihiko Fukushima include Kansai University & Mitsubishi Electric.
Papers
More filters
Journal ArticleDOI
Neocognitron for handwritten digit recognition
TL;DR: This paper proposes an improved version of the neocognitron and tests its ability using a large database of handwritten digits (ETL1) to improve the recognition rate and removes accessory circuits that were appended to the previous versions.
Journal ArticleDOI
Restoring partly occluded patterns: a neural network model
TL;DR: A neural network model that has an ability to restore missing portions of partly occluded patterns and tries to complete even an unlearned pattern by interpolating and extrapolating visible edges.
Journal ArticleDOI
Use of non-uniform spatial blur for image comparison: symmetry axis extraction
TL;DR: This paper shows that the introduction of non-uniform blur is very useful for comparing images, and proposes a neural network model that extracts axes of symmetry from visual patterns, which greatly increases robustness against deformations and various kinds of noise, and largely reduces computational cost.
Journal ArticleDOI
Neocognitron capable of incremental learning
TL;DR: A new neocognitron is proposed that accepts incremental learning, without giving a severe damage to old memories or reducing learning speed, and the learning of all stages of the hierarchical network progresses simultaneously.
Journal ArticleDOI
Increasing robustness against background noise
TL;DR: Computer simulation shows that the new neocognitron is much more robust against background noise than the conventional ones, and the use of subtractive inhibition to S-cells from V-cells is proposed.