Unification neural networks: unification by error-correction learning
Logic Journal of the IGPL 19 (6):821-847 (2011)
Abstract
We show that the conventional first-order algorithm of unification can be simulated by finite artificial neural networks with one layer of neurons. In these unification neural networks, the unification algorithm is performed by error-correction learning. Each time-step of adaptation of the network corresponds to a single iteration of the unification algorithm. We present this result together with the library of learning functions and examples fully formalised in MATLAB Neural Network ToolboxMy notes
Similar books and articles
Dynamical learning algorithms for neural networks and neural constructivism.Enrico Blanzieri - 1997 - Behavioral and Brain Sciences 20 (4):559-559.
Unification: What is it, how do we reach and why do we want it?Erik Weber - 1999 - Synthese 118 (3):479-499.
Some Neural Networks Compute, Others Don't.Gualtiero Piccinini - 2008 - Neural Networks 21 (2-3):311-321.
On the complexity of Bounded Second-Order Unification and Stratified Context Unification.Jordi Levy, Manfred Schmidt-schauß & Mateu Villaret - 2011 - Logic Journal of the IGPL 19 (6):763-789.
The causal and unification approaches to explanation unified—causally.Michael Strevens - 2004 - Noûs 38 (1):154–176.
On the structure of explanatory unification: the case of geographical economics.Uskali Mäki & Caterina Marchionni - 2009 - Studies in History and Philosophy of Science Part A 40 (2):185-195.
Newton’s notion and practice of unification.Steffen Ducheyne - 2005 - Studies in History and Philosophy of Science Part A 36 (1):61-78.
Unification in modal and description logics.Franz Baader & Silvio Ghilardi - 2011 - Logic Journal of the IGPL 19 (6):705-730.
On stability and solvability (or, when does a neural network solve a problem?).Stan Franklin & Max Garzon - 1992 - Minds and Machines 2 (1):71-83.
Highly constrained unification grammars.Daniel Feinstein & Shuly Wintner - 2008 - Journal of Logic, Language and Information 17 (3):345-381.
Neural Network Learning as an Inverse Problem.Věra Kůrková - 2005 - Logic Journal of the IGPL 13 (5):551-559.
Selection and the extent of explanatory unification.Robert A. Skipper - 1999 - Philosophy of Science 66 (3):209.
From the indirect confirmation of theories to theory unification.Luca Moretti - 2004 - Kriterion - Journal of Philosophy 1 (18):10-14.
Introduction: From legal theories to neural networks and fuzzy reasoning. [REVIEW]Lothar Philipps & Giovanni Sartor - 1999 - Artificial Intelligence and Law 7 (2-3):115-128.
Analytics
Added to PP
2015-02-04
Downloads
8 (#989,820)
6 months
1 (#455,921)
2015-02-04
Downloads
8 (#989,820)
6 months
1 (#455,921)
Historical graph of downloads
