Interpolation coding: A representation for numbers in neural models (Q580249): Difference between revisions

From MaRDI portal
Importer (talk | contribs)
Created a new Item
 
Importer (talk | contribs)
Changed an Item
Property / review text
 
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.
Property / review text: 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. / rank
 
Normal rank
Property / Mathematics Subject Classification ID
 
Property / Mathematics Subject Classification ID: 91E99 / rank
 
Normal rank
Property / Mathematics Subject Classification ID
 
Property / Mathematics Subject Classification ID: 68T99 / rank
 
Normal rank
Property / Mathematics Subject Classification ID
 
Property / Mathematics Subject Classification ID: 68T05 / rank
 
Normal rank
Property / Mathematics Subject Classification ID
 
Property / Mathematics Subject Classification ID: 92Cxx / rank
 
Normal rank
Property / Mathematics Subject Classification ID
 
Property / Mathematics Subject Classification ID: 91E30 / rank
 
Normal rank
Property / Mathematics Subject Classification ID
 
Property / Mathematics Subject Classification ID: 94A99 / rank
 
Normal rank
Property / zbMATH DE Number
 
Property / zbMATH DE Number: 4016674 / rank
 
Normal rank
Property / zbMATH Keywords
 
interpolation coding
Property / zbMATH Keywords: interpolation coding / rank
 
Normal rank
Property / zbMATH Keywords
 
neural models
Property / zbMATH Keywords: neural models / rank
 
Normal rank
Property / zbMATH Keywords
 
perception
Property / zbMATH Keywords: perception / rank
 
Normal rank
Property / zbMATH Keywords
 
computing hierarchies of invariants
Property / zbMATH Keywords: computing hierarchies of invariants / rank
 
Normal rank
Property / zbMATH Keywords
 
levels of abstraction
Property / zbMATH Keywords: levels of abstraction / rank
 
Normal rank
Property / zbMATH Keywords
 
value units
Property / zbMATH Keywords: value units / rank
 
Normal rank
Property / zbMATH Keywords
 
encoding
Property / zbMATH Keywords: encoding / rank
 
Normal rank
Property / zbMATH Keywords
 
functional mappings
Property / zbMATH Keywords: functional mappings / rank
 
Normal rank

Revision as of 17:37, 1 July 2023

scientific article
Language Label Description Also known as
English
Interpolation coding: A representation for numbers in neural models
scientific article

    Statements

    Interpolation coding: A representation for numbers in neural models (English)
    0 references
    0 references
    1987
    0 references
    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.
    0 references
    interpolation coding
    0 references
    neural models
    0 references
    perception
    0 references
    computing hierarchies of invariants
    0 references
    levels of abstraction
    0 references
    value units
    0 references
    encoding
    0 references
    functional mappings
    0 references

    Identifiers

    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references