Literature DB >> 3435727

Interpolation coding: a representation for numbers in neural models.

D H Ballard1.   

Abstract

A central task of perception can be defined as one of computing hierarchies of invariants. One way of representing such invariants in intermediate levels of abstraction in this hierarchy is to use discrete units. These have been termed value units. A problem with such an encoding is that there has not been a good way to represent accurate numerical quantities using these units. This paper remedies the deficiency by describing a scheme that interpolates values between units representing fixed numerical quantities. The scheme has nice properties: it extends across functional mappings and it allows different sources of evidence to be combined.

Mesh:

Year:  1987        PMID: 3435727     DOI: 10.1007/BF00354984

Source DB:  PubMed          Journal:  Biol Cybern        ISSN: 0340-1200            Impact factor:   2.086


  13 in total

1.  Stochastic relaxation, gibbs distributions, and the bayesian restoration of images.

Authors:  S Geman; D Geman
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  1984-06       Impact factor: 6.226

2.  Optimization by simulated annealing.

Authors:  S Kirkpatrick; C D Gelatt; M P Vecchi
Journal:  Science       Date:  1983-05-13       Impact factor: 47.728

3.  Adaptation alters perceived direction of motion.

Authors:  E Levinson; R Sekuler
Journal:  Vision Res       Date:  1976       Impact factor: 1.886

4.  On the foundations of relaxation labeling processes.

Authors:  R A Hummel; S W Zucker
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  1983-03       Impact factor: 6.226

5.  Inherent bias and noise in the hough transform.

Authors:  C M Brown
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  1983-05       Impact factor: 6.226

6.  Single units and sensation: a neuron doctrine for perceptual psychology?

Authors:  H B Barlow
Journal:  Perception       Date:  1972       Impact factor: 1.490

7.  Parallel visual computation.

Authors:  D H Ballard; G E Hinton; T J Sejnowski
Journal:  Nature       Date:  1983 Nov 3-9       Impact factor: 49.962

8.  Neural networks and physical systems with emergent collective computational abilities.

Authors:  J J Hopfield
Journal:  Proc Natl Acad Sci U S A       Date:  1982-04       Impact factor: 11.205

9.  "Neural" computation of decisions in optimization problems.

Authors:  J J Hopfield; D W Tank
Journal:  Biol Cybern       Date:  1985       Impact factor: 2.086

10.  Neurons with graded response have collective computational properties like those of two-state neurons.

Authors:  J J Hopfield
Journal:  Proc Natl Acad Sci U S A       Date:  1984-05       Impact factor: 11.205

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.