Neuro-symbolic Representation of Logic Programs Defining Infinite Sets
نویسندگان
چکیده
It has been one of the great challenges of neuro-symbolic integration to represent recursive logic programs using neural networks of finite size. In this paper, we propose to implement neural networks that can process recursive programs viewed as inductive definitions.
منابع مشابه
Using Logic Programs to Reason about Infinite Sets
Using the ideas from current investigations in Knowledge Representation we study the use of a class of logic programs for reasoning about infinite sets. Those programs assert codes for various infinite sets. Depending on the form of atoms allowed in the bodies of clauses we obtain a variety of completeness results for various classes of arithmetic sets of integers.
متن کاملAnswers Synthesis for CLP with Negation
Rewrite techniques can be used to execute logic programs in order to avoid some drawbacks of classical Prolog resolution. Logic programs are represented as rewrite programs whose operational mechanism, inspired from Knuth-Bendix completion, allows to prune some unnecessary computations and offers a synthesis ability which enables to represent infinite sets of answers as finite sets of formulas....
متن کاملA Model-Theoretic Counterpart of Loop Formulas
In an important recent paper, Lin and Zhao introduced the concept of a loop formula, and showed that the answer sets for a logic program are exactly the models of Clark’s completion of the program that satisfy the loop formulas. Just as supported sets are a model-theoretic account of completion, “externally supported” sets, defined in this paper, are a model-theoretic counterpart of loop formul...
متن کاملProperties of Petri Nets Modellings : the temporal way
The traditional proof methods used to verify that a modelling is in accordance with a set of properties expressed in a temporal logic, are restricted to systems with a reasonable number of states. It is possible to overcome this limitation by the structuring of the states space consisting in defining a symbolic representation. In this context, such a representation is a finite representation of...
متن کاملSHERLOCK - An Inteface for Neuro-Symbolic Networks∗
We propose SHERLOCK a novel problemsolving application based on neuro-symbolic networks. The application takes a knowledge base and rules in the form of a logic program, and compiles it into a connectionist neural network that performs computations. The network’s output signal is then translated back into logical form. SHERLOCK allows to compile logic programs either to classical neuro-symbolic...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010