Further arguments in support of localist coding in connectionist networks

Behavioral and Brain Sciences 23 (4):471-471 (2000)
Abstract
Two additional sources of evidence are provided in support of localist coding within connectionist networks. First, only models with localist codes can currently represent multiple pieces of information simultaneously or represent order among a set of items on-line. Second, recent priming data appear problematic for theories that rely on distributed representations. However, a faulty argument advanced by Page is also pointed out.
Keywords No keywords specified (fix it)
Categories (categorize this paper)
DOI 10.1017/S0140525X00253351
Options
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

Our Archive


Upload a copy of this paper     Check publisher's policy     Papers currently archived: 33,142
Through your library

References found in this work BETA

No references found.

Add more references

Citations of this work BETA

No citations found.

Add more citations

Similar books and articles

Hidden Markov Model Interpretations of Neural Networks.Ingmar Visser - 2000 - Behavioral and Brain Sciences 23 (4):494-495.
Neurons Amongst the Symbols?C. Philip Beaman - 2000 - Behavioral and Brain Sciences 23 (4):468-470.
Localist Models Are Already Here.Stellan Ohlsson - 2000 - Behavioral and Brain Sciences 23 (4):486-487.
Localist Representations and Theoretical Clarity.Norman D. Cook - 2000 - Behavioral and Brain Sciences 23 (4):474-475.
Localist Network Modelling in Psychology: Ho-Hum or Hm-M-M?Craig Leth-Steensen - 2000 - Behavioral and Brain Sciences 23 (4):484-485.
Connectionist Modelling in Psychology: A Localist Manifesto.Mike Page - 2000 - Behavioral and Brain Sciences 23 (4):443-467.

Analytics

Added to PP index
2009-01-28

Total downloads
22 ( #263,934 of 2,242,171 )

Recent downloads (6 months)
9 ( #43,500 of 2,242,171 )

How can I increase my downloads?

Monthly downloads

My notes

Sign in to use this feature