How to Upgrade Propositional Learners to First Order Logic: A Case Study

نویسندگان

  • Wim Van Laer
  • Luc De Raedt
چکیده

We describe a methodology for upgrading existing attribute value learners towards rst order logic. This method has several advantages: one can proot from existing research on propositional learners (and inherit its eeciency and eeectiveness), relational learners (and inherit its expressiveness) and PAC-learning (and inherit its theoretical basis). Moreover there is a clear relationship between the new relational system and its propositional counterpart. This makes the ILP system easy to use and understand by users familiar with the propositional counterpart. We demonstrate the methodology on the ICL system which is an upgrade of the propositional learner CN2. Abstract We describe a methodology for upgrading existing attribute value learners towards rst order logic. This method has several advantages: one can proot from existing research on propositional learners (and inherit its eeciency and eeectiveness), relational learners (and inherit its expressive-ness) and PAC-learning (and inherit its theoretical basis). Moreover there is a clear relationship between the new relational system and its proposi-tional counterpart. This makes the ILP system easy to use and understand by users familiar with the propositional counterpart. We demonstrate the methodology on the ICL system which is an upgrade of the propositional learner CN2.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Equality propositional logic and its extensions

We introduce a new formal logic, called equality propositional logic. It has two basic connectives, $boldsymbol{wedge}$ (conjunction) and $equiv$ (equivalence). Moreover, the $Rightarrow$ (implication) connective can be derived as $ARightarrow B:=(Aboldsymbol{wedge}B)equiv A$. We formulate the equality propositional logic and demonstrate that the resulting logic has reasonable properties such a...

متن کامل

A Methodology for Rst Order Learning: a Case Study

Many well-known learning systems like CN2 and C4.5 use an attribute-value representation for the examples. In Inductive Logic Programming (ILP) a rst-order logical formalism is used, which is a more expressive representation. We will introduce a 5-step methodology to upgrade an existing propositional learner towards a rst-order learning system. The system ICL (Inductive Classiication Logic) is ...

متن کامل

Probabilistic reasoning with terms

Many problems in artificial intelligence can be naturally approached by generating and manipulating probability distributions over structured objects. In this paper we represent structured objects by first-order logic terms (lists, trees, tuples, and nestings thereof) and higher-order terms (sets, multisets), and we study the question how to define probability distributions over such terms. We ...

متن کامل

Relational Knowledge Extraction from Attribute-Value Learners

Bottom Clause Propositionalization (BCP) is a recent propositionalization method which allows fast relational learning. Propositional learners can use BCP to obtain accuracy results comparable with Inductive Logic Programming (ILP) learners. However, differently from ILP learners, what has been learned cannot normally be represented in first-order logic. In this paper, we propose an approach an...

متن کامل

First-order Decomposition Trees

Lifting attempts to speedup probabilistic inference by exploiting symmetries in the model. Exact lifted inference methods, like their propositional counterparts, work by recursively decomposing the model and the problem. In the propositional case, there exist formal structures, such as decomposition trees (dtrees), that represent such a decomposition and allow us to determine the complexity of ...

متن کامل

ذخیره 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 2001