Synthese 142 (2):143 - 174 (2004)
|Abstract||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||No keywords specified (fix it)|
|Categories||No categories specified (fix it)|
|Through your library||Configure|
Similar books and articles
Stan Franklin & Max Garzon (1992). On Stability and Solvability (or, When Does a Neural Network Solve a Problem?). Minds and Machines 2 (1).
Enrico Blanzieri (1997). Dynamical Learning Algorithms for Neural Networks and Neural Constructivism. Behavioral and Brain Sciences 20 (4):559-559.
Roger Sansom (2008). The Connectionist Framework for Gene Regulation. Biology and Philosophy 23 (4):475-491.
Paul Skokowski (2007). Networks with Attitudes. Artificial Intelligence and Society 22 (3):461-470.
Jonathan Opie & Gerard O'Brien (2006). How Do Connectionist Networks Compute? Cognitive Processing 7 (1):30-41.
Dan Hunter (1999). Out of Their Minds: Legal Theory in Neural Networks. Artificial Intelligence and Law 7 (2-3).
Hannes Leitgeb (2005). Interpreted Dynamical Systems and Qualitative Laws: From Neural Networks to Evolutionary Systems. Synthese 146 (1-2):189 - 202.
Hannes Leitgeb (2004). Inference on the Low Level: An Investigation Into Deduction, Nonmonotonic Reasoning, and the Philosophy of Cognition. Kluwer Academic Publishers.
Gualtiero Piccinini (2008). Some Neural Networks Compute, Others Don't. Neural Networks 21 (2-3):311-321.
Added to index2009-01-28
Total downloads5 ( #160,368 of 549,093 )
Recent downloads (6 months)0
How can I increase my downloads?