How to Specialize by Theory Refinement

نویسنده

  • Claire Nedellec
چکیده

* Over-generalization is a well-known problem in empirical learning. Incremental and cautious generalization may limit it, but the concept description language may be incomplete or incorrect. In this case, overgeneralization may indicate that the language must be improved. This paper presents an interactive incremental learning method with a "smallest generalization steps" strategy such that whenever a learned concept is overgeneral, the method specializes it and efficiently helps a user to identify the insufficiencies of the concept language and in improving it if necessary.

برای دانلود 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

Refinement to the Existing Analytical Methods of Analysis of Buried Pipelines due to Strike-Slip Faulting

Analytical methods presented to analyze the buried steel pipelines at strike-slip fault crossing use the Euler-Bernoulli beam theory. The cross-section of a buried pipe that is completely surrounded by soil cannot rotate freely and would not be remained perpendicular to the bending line after deformation. So it would be better to take into consideration a rotation between the cross-section and ...

متن کامل

Verification of Hybrid Automata by Synthesis and Refinement

We present a verification technique to check properties of systems in the model of Linear Hybrid Automata. Given an automaton synthesized from a logic formula, we stepwise specialize transitions and states by operations which preserve the language accepted by the original automaton. We define a proof system based on refinement technique that preserves the properties of the original automaton, a...

متن کامل

Generalizing Refinement Operators to Learn Prenex Conjunctive Normal Forms

Inductive Logic Programming considers almost exclusively universally quantied theories. To add expressiveness, prenex conjunctive normal forms (PCNF) with existential variables should also be considered. ILP mostly uses learning with refinement operators. To extend refinement operators to PCNF, we should first do so with substitutions. However, applying a classic substitution to a PCNF with exi...

متن کامل

Microstructure and Grain Refining Performance of a New Al-Ti-C Master Alloy (RESEARCH NOTE)

Control of microstructure parameters that affecting the Al-Ti-C master alloys grain refining efficiency is leading to improve the aluminum grain refinement. This study was an attempt to produce Al-Ti-C master alloys that provide these controlling factors with relying on the solute effect theory. The produced master alloys were examined by using scanning electron microscopy (SEM), energy-dispers...

متن کامل

Why Has Inequality Increased in China? toward a Theory of International Matching∗

It seems entirely fitting to discuss the Chinese economy on this occasion of the opening of the Renmin-Monash Advanced Centre of Economic Studies (ACES). One of the most striking features of that economy is the remarkable pace at which it has grown in the past one or two decades. A real challenge for economists is to account for this extraordinary success story. I think that a potentially signi...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1992