A Rule Extraction Algorithm That Scales Between Fidelity and Comprehensibility
نویسندگان
چکیده
منابع مشابه
A Survey on Rule Extraction for Achieving a Trade off Between Accuracy and Comprehensibility
machine have demonstrated superior performance to many other classification techniques in a variety of application areas. However, they provide highly accurate model but they have an inability to provide an explanation, or comprehensible justification, for the solutions they provide as the output produce is in the form of weights and nodes [2]. Some techniques like decision tree provide compreh...
متن کاملRule Extraction with Guaranteed Fidelity
This paper extends the conformal prediction framework to rule extraction, making it possible to extract interpretable models from opaque models in a setting where either the infidelity or the error rate is bounded by a predefined significance level. Experimental results on 27 publicly available data sets show that all three setups evaluated produced valid and rather efficient conformal predicto...
متن کاملUsing rule extraction to improve the comprehensibility of predictive models
Whereas newer machine learning techniques, like artificial neural networks and support vector machines, have shown superior performance in various benchmarking studies, the application of these techniques remains largely restricted to research environments. A more widespread adoption of these techniques is foiled by their lack of explanation capability which is required in some application area...
متن کاملreCORE - A Coevolutionary Algorithm for Rule Extraction
A coevolutionary algorithm called reCORE for rule extraction from databases was proposed in the paper. Knowledge is extracted in the form of simple implication rules IF-THEN-ELSE. There are two populations involved, one for rules and second for rule sets. Each population has a distinct evolution scheme. One individual from rule set population and a number of individuals from rule population con...
متن کاملA Bayesian Unsupervised Learning Algorithm that Scales
A persistent worry with computational models of unsupervised learning is that learning will become more difficult as the problem is scaled. We examine this issue in the context of a novel hierarchical, generative model that can be viewed as a nonlinear generalization of factor analysis and can be implemented in a neural network. The model performs perceptual inference in a probabilistically con...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Asian Journal of Scientific Research
سال: 2012
ISSN: 1992-1454
DOI: 10.3923/ajsr.2012.121.132