Connectionist Unifying Prolog
نویسنده
چکیده
We introduce an connectionist approach to uniica-tion using a local and a distributed representation. A Prolog-System using these uniication-strategies has been build. Prolog is a Logic Programming Language which utilizes uniication. We introduce a uncertainty measurement in uniication. This measurement is based on the structure-abilities of the chosen representations. The strategy using a local representation, called`-CUP, utilizes a self-organizing feature-map (FM-net) to determine similarities between terms and induces the representation for a relaxation-network (relax-net). The strategy using a distributed representation , called d-CUP, embeds a similarity measurement by its recurrent representation. It has the advantage that similar terms have a similar representation. The uniication itself is done by a back-propagation network (BP-net). We have proven the systems adequacy for uniica-tion, its eecient computation, and the ability to do extended uniication.
منابع مشابه
Optimizing Logical Proofs with Connectionist Networks
We describe a connectionist approach to extract control knowledge from Prolog programs in order to utilize it for new proofs. A metainterpreter encodes successful Prolog proofs as training patterns for neural networks. Trained with these examples, the different connectionist networks store control strategies to select clauses and literals. A second metainterpreter uses the networks to improve t...
متن کاملConnectionist Uniication with a Distributed Representation
This paper presents a connectionist uniication strategy for a Prolog-system. The uniication strategy utilizes a backprop-net (bp-net) and a distributed connectionist representation. The most-general-uniier is computed by the connectionist heuristic in constant time. To keep the system also eecient in space the distributed representation was choosen. It is possible to show that this representati...
متن کاملA Unifying View of Structural Induction and Computation Induction for Logic Programs
In the framework of Extended Prolog Execution K&S 86] a rule of Structural Induction is presented. For the induction step the new rule takes advantage of a Prolog program synthesized through Proof-Extraction techniques , and rests on extensive use of Negation as Failure Inference for exploiting the information contained in the extracted program. We describe how to synthesize Prolog procedures w...
متن کاملLogical Vs.analogical or Symbolic vs. Connectionist or Neat vs. Scruffy
Minsky subscribes to neither of these extremist views. Instead, he argues that Artificial Intelligence must employ many approaches. Artificial Intelligence is not like circuit theory and electromagnetism. There is nothing wonderfully unifying like Kirchhoff's laws are to circuit theory or Maxwell's equations are to electromagnetism. Instead of looking for a "Right Way", Minsky believes that the...
متن کاملConnectionist modeling of developmental changes in infancy: approaches, challenges, and contributions.
Connectionist models have been applied to many phenomena in infant development including perseveration, language learning, categorization, and causal perception. In this article, we discuss the benefits of connectionist networks for the advancement of theories of early development. In particular, connectionist models contribute novel testable predictions, instantiate the theorized mechanism of ...
متن کامل