Rule Extraction: From Neural Architecture to Symbolic Representation
نویسندگان
چکیده
منابع مشابه
Rule Extraction: From Neural Representation Architecture to Symbolic
This paper shows how knowledge, in the form of fuzzy rules, can be derizted from a superuised learning neural network called fuzzy ARTMAP. Rule extraction proceeds in two stages: pruning, which simplifies the network structure by remooing excessiae recognition categories and weights; and quantization of continuous learned weights, which allows the final system state to be translated into a usab...
متن کاملSymbolic Rule Representation in Neural Network Models
Symbolic knowledge extraction from mapping/extrapolating neural networks is presented in the paper. An algorithm to obtain crisp rules in the form of logical implications which roughly describe the neural network mapping is introduced. The number of extracted rules can be selected using an uncertainty margin parameter as well as by changing the precision of the soft quantization of the inputs. ...
متن کاملRule Extraction from Neural Networks
The artificial neural networks (ANNs) are well suitable to solve a variety class of problems in a knowledge discovery field (e.g., in natural language processing) because the trained networks are more accurate at classifying the examples that represent a problem domain. However, the neural networks that consist of large number of weighted connections (called also links) and activation units oft...
متن کاملRule Extraction from Recurrent Neural Networks using a Symbolic Machine Learning Algorithmy
This paper addresses the extraction of knowledge from recurrent neural networks trained to behave like deterministic nite-state automata (DFAs). To date, methods used to extract knowledge from such networks have relied on the hypothesis that networks states tend to cluster and that clusters of network states correspond to DFA states. The computational complexity of such a cluster analysis has l...
متن کاملRule extraction from recurrent neural networks
This thesis investigates rule extraction from recurrent neural networks, which takes the form of automated construction of models of an underlying network. Typically the models are expressed as finite state machines and they should mimic the network while being more intelligible. It is argued that rule extraction allows a deeper and more general form of analysis than other, more or less ad hoc,...
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: Connection Science
سال: 1995
ISSN: 0954-0091,1360-0494
DOI: 10.1080/09540099508915655