Synthese 142 (2):143-174 (2004)

There is a gap between two different modes of computation: the symbolic mode and the subsymbolic (neuron-like) mode. The aim of this paper is to overcome this gap by viewing symbolism as a high-level description of the properties of (a class of) neural networks. Combining methods of algebraic semantics and non-monotonic logic, the possibility of integrating both modes of viewing cognition is demonstrated. The main results are (a) that certain activities of connectionist networks can be interpreted as non-monotonic inferences, and (b) that there is a strict correspondence between the coding of knowledge in Hopfield networks and the knowledge representation in weight-annotated Poole systems. These results show the usefulness of non-monotonic logic as a descriptive and analytic tool for analyzing emerging properties of connectionist networks. Assuming an exponential development of the weight function, the present account relates to optimality theory – a general framework that aims to integrate insights from symbolism and connectionism. The paper concludes with some speculations about extending the present ideas.
Keywords Philosophy   Philosophy   Epistemology   Logic   Metaphysics   Philosophy of Language
Categories (categorize this paper)
Reprint years 2005
DOI 10.1007/s11229-004-1929-y
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

PhilArchive copy

Upload a copy of this paper     Check publisher's policy     Papers currently archived: 60,842
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

On the Proper Treatment of Connectionism.Paul Smolensky - 1988 - Behavioral and Brain Sciences 11 (1):1-23.
Darwin's Dangerous Idea.Daniel C. Dennett - 1996 - Behavior and Philosophy 24 (2):169-174.
A Logical Calculus of the Ideas Immanent in Nervous Activity.Warren S. McCulloch & Walter Pitts - 1943 - The Bulletin of Mathematical Biophysics 5 (4):115-133.

View all 17 references / Add more references

Citations of this work BETA

Illustrating a Neural Model of Logic Computations: The Case of Sherlock Holmes’ Old Maxim.Eduardo Mizraji - 2016 - Theoria: Revista de Teoría, Historia y Fundamentos de la Ciencia 31 (1):7-25.
A Computational Learning Semantics for Inductive Empirical Knowledge.Kevin T. Kelly - 2014 - In Alexandru Baltag & Sonja Smets (eds.), Johan van Benthem on Logic and Information Dynamics. Springer International Publishing. pp. 289-337.

Add more citations

Similar books and articles

Some Neural Networks Compute, Others Don't.Gualtiero Piccinini - 2008 - Neural Networks 21 (2-3):311-321.
Out of Their Minds: Legal Theory in Neural Networks. [REVIEW]Dan Hunter - 1999 - Artificial Intelligence and Law 7 (2-3):129-151.
Nonmonotonic Theories and Their Axiomatic Varieties.Zbigniew Stachniak - 1995 - Journal of Logic, Language and Information 4 (4):317-334.
Nonmonotonic Inconsistency.Charles B. Cross - 2003 - Artificial Intelligence 149 (2):161-178.


Added to PP index

Total views
78 ( #133,842 of 2,438,879 )

Recent downloads (6 months)
3 ( #209,001 of 2,438,879 )

How can I increase my downloads?


My notes