๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

A self-organising neural network model of image velocity encoding

โœ Scribed by K. N. Gurney; M. J. Wright

Publisher
Springer-Verlag
Year
1992
Tongue
English
Weight
959 KB
Volume
68
Category
Article
ISSN
0340-1200

No coin nor oath required. For personal study only.

โœฆ Synopsis

A self-organising neural network has been developed which maps the image velocities of rigid objects, moving in the fronto-parallel plane, topologically over a neural layer. The input is information in the Fourier domain about the spatial components of the image. The computation performed by the network may be viewed as a neural instantiation of the Intersection of Constraints solution to the aperture problem. The model has biological plausibility in that the connectivity develops simply as a result of exposure to inputs derived from rigid translation of textures and its overall organisation is consistent with psychophysical evidence.

I Note that, 'direction' is specified throughout a complete circular range from 0-360 ~ , and should be distinguished from 'orientation' which is usually specified in a half-circular interval and is directionally ambiguous

๐Ÿ“œ SIMILAR VOLUMES

A self-organizing neural network model f
A self-organizing neural network model for the development of complex cells
โœ Takashi Nagano; Koji Kurata ๐Ÿ“‚ Article ๐Ÿ“… 1981 ๐Ÿ› Springer-Verlag ๐ŸŒ English โš– 444 KB

On the basis of recent neurophysiological findings on the mammalian visual cortex, a selforganizing neural network model is proposed for the understanding of the development of complex cells. The model is composed of two kinds of connections from LGN cells to a complex cell. One is direct excitatory

A neural-network-based model for 2D micr
A neural-network-based model for 2D microwave imaging of cylinders
โœ Kun-Chou Lee ๐Ÿ“‚ Article ๐Ÿ“… 2004 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 97 KB

In this article, a neural network with radial-basis functions (RBF-NN) is applied to microwave imaging of cylinders. Initially, the shape function of the target cylinder is expanded by a Fourier series. The RBF-NN is trained by some direct-scattering data sets and thus can predict the images of the

A layered neural network interfaced with
A layered neural network interfaced with a cochlear model for the study of speech encoding in the auditory system
โœ H. Sheikhzadeh; L. Deng ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 599 KB

Our recent development of a computational cochlear-nucleus-like network model for the study of speech encoding mechanisms associated with parts of the auditory system central to the auditory nerve is described in this paper. This network model is based on physiological grounds, and is designed to gr