Connectionist Semantics and the Collateral Information Challenge

@article{Garzoan2003ConnectionistSA,
  title={Connectionist Semantics and the Collateral Information Challenge},
  author={Francisco Calvo Garzoan},
  journal={Mind \& Language},
  year={2003},
  volume={18},
  pages={77-94}
}
Jerry Fodor and Ernest Lepore have launched a powerful attack against Paul Churchland's connectionist theory of semantics - aka State Space Semantics. In one part of their overall attack, they exploit the potentially orthogonal histories of different individuals to introduce what they labeled 'the collateral information problem'. Aarre Laakso and Gary Cottrell have recently put forward a mathematical technique for measuring conceptual similarity across neural networks. Churchland uses Laakso… 

Figures and Tables from this paper

Empirical Lessons for Philosophical Theories of Mental Content
TLDR
This thesis concerns the content of mental representations and draws lessons for philosophical theories of content from some empirical findings about brains and behaviour drawn from experimental psychology, cognitive neuroscience and cognitive science, and some of the representational systems found in real brains.
Context-free versus Context-Dependent Constituency Relations: A False Dichotomy
In this paper I articulate a notion of constituency orthogonal both to classical and connectionist approaches. I shall consider three “structure-in-time” connectionist networks (Simple Recurrent
Towards a General Theory of Antirepresentationalism
  • F. Garzón
  • Psychology
    The British Journal for the Philosophy of Science
  • 2008
This work represents an attempt to stake out the landscape for dynamicism based on a radical dismissal of the information-processing paradigm that dominates the philosophy of cognitive science. In
Where is Cognitive Science Heading?
According to Ramsey (Representation reconsidered, Cambridge University Press, New York, 2007), only classical cognitive science, with the related notions of input–output and structural
Content and Its Vehicles in Connectionist Systems
This paper advocates explicitness about the type of entity to be considered as contentbearing in connectionist systems; it makes a positive proposal about how vehicles of content should be
Content and Its Vehicles in Connectionist Systems
This paper advocates explicitness about the type of entity to be considered as contentbearing in connectionist systems; it makes a positive proposal about how vehicles of content should be
Content and its vehicles in connectionist systems
TLDR
The proposal is that the vehicles of content in some connectionist systems are clusters in the state space of a hidden layer that are required to vindicate the standard explanation for some classificatory networks’ ability to generalise to novel samples their correct classification of the samples on which they were trained.
Semi-supervised learning for connectionist networks
TLDR
This work examines the semi-supervised learning paradigm as the most accurate computational description of the environmental conditions of lexical acquisition during language development and argues that its real ecological validity and occasional improvements in performance over supervised learning make it an ideal candidate for modeling of language acquisition and other learning problems.
A Critique of the Similarity Space Theory of Concepts
:  A similarity space is a hyperspace in which the dimensions represent various dimensions on which objects may differ. The similarity space theory of concepts is the thesis that concepts are regions

References

SHOWING 1-10 OF 17 REFERENCES
State space semantics and conceptual similarity: Reply to Churchland
Jerry Fodor and Ernest Lepore [(1992) Holism: a shopper's guide, Oxford: Blackwell; (1996) in R. McCauley (Ed.) The Churchlands and their critics , Cambridge: Blackwell] have launched a powerful
The Churchlands and their critics
Introduction. Part I: Essays Addressed to the Churchlands:. 1. Explanatory Pluralism and the Co--evolution of Theories in Science: Robert N McCauley (Emory University). 2. From Neurophilosophy to
Content and cluster analysis: Assessing representational similarity in neural systems
TLDR
This paper argues that the correct way to compare neural representations is through analysis of the distances between neural activations, and presents a method for doing so, and uses the technique to demonstrate empirically that different artificial neural networks trained by backpropagation on the same categorization task, even with different representational encodings of the input patterns and different numbers of hidden units, reach states in which representations at the hidden units are similar.
All at sea in semantic space : Churchland on meaning similarity
Critique de la notion de similarite du contenu qui caracterise les theories semantiques contemporaines. Mettant en evidence la non-pertinence de l'idee de similarite du point de vue des theories de
Conceptual similarity across sensory and neural diversity : The Fodor/Lepore challenge answered
Reponse a la critique de la semantique de l'etat-espace, consideree comme modele du reseau neuronal, developpee par J. Fodor et E. Lepore dans leur ouvrage intitule «Holism: a shopper's guide»
Introduction to Connectionist Modelling of Cognitive Processes
TLDR
This work focuses on connectionist neuropsychology - lesioning neural networks and the appeal of parallel distributed processing for modelling cognition.
Connectionism and the mind: An introduction to parallel processing in networks
TLDR
Critiques and defences of connectionism connectionism and the disciplines of cognitive science.
Generalization , simple recurrent networks , and the emergence of structure
The problem is that most human behaviors seem to lie somewhere between these two possibilities. Neither lists nor rules capture the richness of cognitive behaviors, which are populated by what Plaut,
Semantics San Diego Style
Evaluation de la semantique de l'etat spatial (state-space semantics) developpee par P. Churchland dans le sens d'un renforcement de la semantique du role conceptuel par une conception solide de la
How Can I Know What You Think ? : Assessing Representational Similarity in Neural Systems
TLDR
A technique for measuring the similarities between representati ons at various layers of neural networks is presented and it is demonstrated empirically that different artificial neura l networks trained by backpropagation on the same categorizatio n task, even with different representational encodings of th e input patterns and different numbers of hidden units, reach st ate in which representations at the hidden units are similar.
...
1
2
...