Application of Hopfield network to saccades

  title={Application of Hopfield network to saccades},
  author={Teruyoshi Washizawa},
  journal={IEEE transactions on neural networks},
  volume={4 6},
  • T. Washizawa
  • Published 1 November 1993
  • Computer Science
  • IEEE transactions on neural networks
Human eye movement mechanisms (saccades) are very useful for scene analysis, including object representation and pattern recognition. A Hopfield neural network for emulating saccades is proposed. The network uses an energy function that includes location and identification tasks. Computer simulation shows that the network performs those tasks cooperatively. The result suggests that the network is applicable to shift-invariant pattern recognition. 

Figures from this paper

An Overview of Neuromorphic Computing for Artificial Intelligence Enabled Hardware-Based Hopfield Neural Network
This paper presents a comprehensive review and focuses extensively on the Hopfield algorithm’s model and its potential advancement in new research applications to facilitate developers with a better understanding of the aforementioned model in accordance to build their own artificial intelligence projects.
A fuzzy Hopfield neural network for medical image segmentation
An unsupervised parallel segmentation approach using a fuzzy Hopfield neural network based on the within-class scatter matrix shows the promising results in comparison with the hard c-means method.
Fuzzy Clustering Using A Compensated Fuzzy Hopfield Network
A CFHNN is proposed which integrates a Compensated Fuzzy C-Means model into the learning scheme and updating strategies of the Hopfield neural network, and shows promising results in comparison with FCM and PFCM methods.
Optimization of object region and boundary extraction by energy minimization for activity recognition
Optimizing Active Contour Model using recurrent architecture for automatic object region and boundary extraction in human activity video sequences is presented and results in an effective segmentation that is less sensitive to noise and complex environments.
A Compensated Fuzzy Hopfield Neural Network for Codebook Design in Vector Quantization
In this paper, a new Hopfield-model net called Compensated Fuzzy Hopfield Neural Network (CFHNN) is proposed for vector quantization in image compression, embedded into Hopfield neural network so that the parallel implementation for codebook design is feasible.
Segmentation of medical images through a penalized fuzzy Hopfield network with moments preservation
The Hopfield neural network with penalized fuzzy c‐means technique (called PFHNN) is proposed for medical image segmentation, where the pixels with their first and second order moments constructed from their n nearest neighbors as a training vector are mapped to a two‐dimensional Hopfield Neural network for the purpose of classifying the image into suitable regions.
The problem of studying pattern recognition techniques for a nalyzing textured surfaces is considered in this thesis and the results a re applied to the classification of steel surfaces according to
Modified Hopfield Networks for Integrated Process Planning and Scheduling
This chapter describes the development and use of DNA profiling for the diagnosis of infectious disease and some of the techniques used to find and identify these diseases are cytotoxic.
An optimal power-dispatching control system for the electrochemical process of zinc based on backpropagation and Hopfield neural networks
This paper describes an optimization problem to minimize the cost of power consumption for the electrochemical process of zinc (EPZ) depending on varying prices of electrical power. A series of


Behavioural constraints on animate vision
  • D. Ballard
  • Psychology, Computer Science
    Image Vis. Comput.
  • 1989
Neural networks and physical systems with emergent collective computational abilities.
  • J. Hopfield
  • Computer Science
    Proceedings of the National Academy of Sciences of the United States of America
  • 1982
A model of a system having a large number of simple equivalent components, based on aspects of neurobiology but readily adapted to integrated circuits, produces a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.
Neural networks for computation: number representations and programming complexity.
It is shown that for some computational problems, the programming complexity may be so great as to limit the utility of neural networks, while for others the investment of computation in programming the network is justified.
Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit
It is described how several optimization problems can be rapidly solved by highly interconnected networks of simple analog processors, and it is shown that a network which solves linear programming Problems can be understood from the same concepts.