2008 Special Issue: Some neural networks compute, others don't

Authors:
Gualtiero Piccinini
Affiliations:
Department of Philosophy, University of Missouri-St. Louis, St. Louis, MO 63121-4400, USA
Venue:
Neural Networks
Year:
2008

Citing 7
Cited 1

A neurocomputational perspective

A neurocomputational perspective
The appeal of parallel distributed processing

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
The computational brain

The computational brain
Computer science as empirical inquiry: symbols and search

Communications of the ACM
General-purpose computation with neural networks: a survey of complexity theoretic results

Neural Computation
Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems

Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems
Approximations of continuous functionals by neural networks with application to dynamic systems

IEEE Transactions on Neural Networks

The Explanatory Role of Computation in Cognitive Science

Minds and Machines

Quantified Score

Hi-index	0.00

Visualization

Abstract

I address whether neural networks perform computations in the sense of computability theory and computer science. I explicate and defend the following theses. (1) Many neural networks compute-they perform computations. (2) Some neural networks compute in a classical way. Ordinary digital computers, which are very large networks of logic gates, belong in this class of neural networks. (3) Other neural networks compute in a non-classical way. (4) Yet other neural networks do not perform computations. Brains may well fall into this last class.