Download:
|
by Boon Toh, Low Norman, Y. Foo
ftp://ftp.cs.su.oz.au/pub/tr/TR94_486.ps.Z
Add To MetaCart
Abstract:
This technical report presents a hybrid symbolic-neural network for representing and reasoning about commonsense beliefs called a Neural-Logic Belief Network (NLBN). Concepts are represented by nodes and relations amongst the concepts are represented by numerical directed links from one node to another. The network computation functions are similar to those of a neural network and classical logical relations such as AND, OR, etc., as well as human biased relations can be modelled by the network. The belief network is four-valued, that is a proposition is either being believed, its negation is believed, unknown or contradictory. Unlike the material implication in logic systems, defeasible IF-THEN rules in this formalism are unidirectional and well behaved; they only express the intended declarative semantics. A set of network operators similar to that of the belief revision operators have been defined and they allow knowledge to be dynamically updated in the knowledge system. This formalism has been implemented using Prolog on a unix machine. Its hybrid network architecture makes inferencing deterministic and efficient. 1
Citations
|
4539
|
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
– Pearl
- 1988
|
|
563
|
The Art of Prolog
– Sterling, Shapiro
- 1986
|
|
547
|
A truth maintenance system
– Doyle
- 1979
|
|
544
|
A framework for representing knowledge
– Minsky
- 1981
|
|
508
|
Introduction to Metamathematics
– Kleene
- 1971
|
|
457
|
Knowledge in Flux. Modeling the Dynamics of Epistemic States
– Gärdenfors
- 1988
|
|
226
|
A useful four-valued logic
– Belnap
- 1977
|
|
196
|
Non-monotonic logic I
– D, Doyle
|
|
183
|
J.R.: Mathematical Logic
– Shoenfield
- 1967
|
|
174
|
Many-Valued Logic
– Rescher
- 1969
|
|
127
|
On the Logic of Theory Change: partial meet functions for contraction and revision
– Alchourrón, Gärdenfors, et al.
- 1985
|
|
94
|
1977] Elements of Intuitionism
– Dummett
|
|
66
|
Possible-world semantics for autoepistemic logic
– Moore
- 1984
|
|
57
|
Non-Monotonic Reasoning: Formalization of Commonsense Reasoning
– Lukaszewicz
- 1990
|
|
55
|
Intuitionism: An introduction
– Heyting
- 1966
|
|
50
|
Knowledge Representation in Fuzzy Logic
– Zadeh
- 1989
|
|
37
|
Multi-valued Logics
– Ginsberg
- 1986
|
|
37
|
A Unified View of Propositional Knowledge Base Updates
– Katsuno, Mendelzon
- 1989
|
|
36
|
An introduction to neural computing
– Kohonen
- 1988
|
|
30
|
Refining symbolic knowledge using neural networks
– Towell, Shavlik
- 1991
|
|
29
|
An Assumption Based TMS
– Kleer
- 1986
|
|
27
|
The Revision Theory of Truth
– Belnap, Gupta
- 1993
|
|
26
|
A course in mathematical logic
– Bell, Machover
- 1977
|
|
5
|
Prolog for Programmers
– Kluzniak, Szpakowicz
- 1985
|
|
4
|
Fuzzy Sets and Falling Shadows of Random Sets
– Wang
- 1985
|
|
3
|
Neural-logic belief networks---a tool for knowledge representation and reasoning
– Low
- 1993
|
|
3
|
Towards a network for representing beliefs
– Low, Foo
- 1992
|
|
3
|
A network formalism for commonsense reasoning
– Low, Foo
- 1993
|
|
2
|
Neural three-valued logic networks
– Chan, Hsu, et al.
- 1989
|
|
2
|
Neural logic networks
– Chan, Hsu, et al.
- 1993
|
|
2
|
A subsumptive inference network for belief representation
– Low
- 1994
|
|
2
|
Perceptrons: An Introduction to Computaional Geometry
– Minsky, Papert
- 1969
|
|
2
|
Programming in neural logic
– Reynolds, Teh, et al.
- 1990
|
