NSL: a Neuro-Symbolic Language for Monotonic and Non-Monotonic Logical Inferences
نویسندگان
چکیده
The complete definition of a Neuro-Symbolic Language, partially introduced in [1], for monotonic and non-monotonic logical inference by means of artificial neural networks (ANNs) is presented. Both the language and its compiler have been designed and implemented. It has been shown that the ANN model here adopted (NFC – Neural Forward Chaining [2]) is a massively parallel abstract interpreter of definite logic programs; moreover, inhibition is used to implement a neural form of logical negation. Previous compiler for translating the neural representation of a given problem into a VHDL software, which in turn can set electronic device like FPGA, has been modified to fit the new and more complete features of the language.
منابع مشابه
A Process Theory of Non-monotonic Inference
Artificial Intelligence needs a formal theory of the process of non-monotonic reasoning. Ideally, such a theory would decide, for every proposition and state of the process, whether the program should believe the proposition in that state, or remain agnostic. Without non-monotonic inference rules, non-monotonic inferences cannot be explained in the same relational, rule-based fashion as other i...
متن کاملCan Formal Non-monotonic Systems Properly Describe Human Reasoning?
Monotonic (logical) reasoning makes the strong claim that an inference cannot be contradicted by future information; an assumption contrary to everyday life experience. This assumption is relaxed in non-monotonic reasoning. However, there are only few formal non-monotonic theories of reasoning that have inspired psychological theory-building. Can formal systems such as cumulative logic (system ...
متن کاملMonotonic and Nonmonotonic Inference for Abstract Argumentation
We present a new approach to reasoning about the outcome of an argumentation framework, where an agent’s reasoning with a framework and semantics is represented by an inference relation defined over a logical labeling language. We first study a monotonic type of inference which is, in a sense, more general than an acceptance function, but equally expressive. In order to overcome the limitations...
متن کاملNon-monotonic reasoning with normative conflicts in multi-agent deontic logic
We present proof-theoretical and semantical characterizations of two multi-agent deontic logics for dealing with normative conflicts. The resulting logics PMDL and PMDL are non-standard in at least two respects. First, they are nonclassical in the sense that they invalidate some inferences of the propositional fragment of Classical Logic (CL). Consequently, they also invalidate certain inferenc...
متن کاملA Sequent Calculus for Intuitionistic Default Logic
Current research on non-monotonic reasoning shows growing interest on implementation details, so the need for concrete calculi formalizing non-monotonic logics is clearly recognized. On the other hand, there is also an increased number of works combining intuitionistic logic with various kinds of non-monotonic formalisms. As a case in point, intuitionistic versions of both default and autoepist...
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 2002