Neocognitron: A neural network model for a mechanism of visual pattern recognition

  title={Neocognitron: A neural network model for a mechanism of visual pattern recognition},
  author={Kunihiko Fukushima and Sei Miyake and Takayuki Ito},
  journal={IEEE Transactions on Systems, Man, and Cybernetics},
A recognition with a large-scale network is simulated on a PDP-11/34 minicomputer and is shown to have a great capability for visual pattern recognition. The model consists of nine layers of cells. The authors demonstrate that the model can be trained to recognize handwritten Arabic numerals even with considerable deformations in shape. A learning-with-a-teacher process is used for the reinforcement of the modifiable synapses in the new large-scale model, instead of the learning-without-a… 
A novel perceptron architecture for simulating object construction
An architecture for the preceptor is proposed in which the neurons' APs are transmitted in structures that represent the stimuli patterns, and the response of connected neuron through their synapses is highly proportional to the nature of these structures.
Multidimensional Hebbian Learning With Temporal Coding in Neocognitron Visual Recognition
  • Y. Lee
  • Computer Science
    IEEE Transactions on Systems, Man, and Cybernetics: Systems
  • 2017
This paper is the first to carry out quantitative analysis of the neuron responses for gray scale image classification, and an analogy is shown between unsupervised Hebbian learning and PCA when applied to the neocognitron model.
Neocognitron for rotated pattern recognition
The layers of the Neocognitron are examined to emphasize their importance in Fukushima's theory and an additional filer layer is provided to deal with rotated patterns.
A new approach for pattern recognition by neural networks with scramblers
An approach to pattern recognition that is based on a concept involving an invariance net and a trainable classifier and some numerical results are illustrated to show the effectiveness of the present algorithm for pattern recognition.
Neural Networks for Region Detection
The paper proposes a neural network organized in three structures, each of which is constituted by a set of levels, which shows good throughput in spite of network complexity.
Learning a dictionary of shape-components in visual cortex: comparison with neurons, humans and machines
This may be the first time that a neurobiological model, faithful to the physiology and the anatomy of visual cortex, not only competes with some of the best computer vision systems thus providing a realistic alternative to engineered artificial vision systems, but also achieves performance close to that of humans in a categorization task involving complex natural images.


Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position
A Biological Approach to Pattern Recognition
  • H. Marko
  • Computer Science
    IEEE Trans. Syst. Man Cybern.
  • 1974
A layer structured system suitable for pattern recognition which operates similar to the afferent nervous system of vertebrates and corresponds approximately to the human capability for this task is described.
Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
This method is used to examine receptive fields of a more complex type and to make additional observations on binocular interaction and this approach is necessary in order to understand the behaviour of individual cells, but it fails to deal with the problem of the relationship of one cell to its neighbours.
Recognition of handwritten characters with a system of homogeneous layers
  • Nachrichtentechnische Zeitschrift, vol. 23, pp. 455-459, Sept. 1970.
  • 1970
Analysis of a Four-Layer Series-Coupled Perceptron. II