Add to ORKG對於神經網路系統將提出一個法則萃取的方式，並從神經網路中得到相關法則。在這裡我們所提到的方法是根據反函數的觀念而得到的。A rule-extraction method of the layered feed-forward neural networks is proposed here for identifying the rules suggested in the network. The method that we propose for the trained layered feed-forward neural network is based on the inversion of the functions computed by each layer of the network. The new rule-extraction method back-propagates regions from the output layer back to the input layer, and we hope that the method can be used further to deal with the predicament of ANN being a black box
Rule extraction from Artificial Neural Networks (ANN's) is an essential step towards the integration...
This last decade multi-layer perceptrons (MLPs) have been widely used in classification tasks. Never...
Artificial neural networks (ANN) have the ability to model input-output relationships from processin...
We propose a mathematical programming methodology for identifying and examining regression rules ext...
Classification and Rule extraction is an important application of Artificial Neural Network. To extr...
神經網路已經被成功地應用於解決各種分類及函數近似的問題，尤其因為神經網路是個萬能的近似器(universal approximator)，所以對於函數近似的問題效果更為顯著。以往對於此類問題雖然多數以...
Two methods of obtaining structured information from a trained feed-forward neural network are discu...
Although backpropagation ANNs generally predict better than decision trees do for pattern classifica...
An important drawback of many artificial neural networks (ANN) is their lack of explanation capabili...
Hybrid intelligent systems that combine knowledge based and artificial neural network systems typica...
In this paper, a learning method for multi-layers neural network in system controller is discussed a...
Despite their success-story, artificial neural networks have one major disadvantage compared to othe...
Search methods for rule extraction from neural networks work by finding those combinations of inputs...
Before symbolic rules are extracted from a trained neural network, the network is usually pruned so ...
This paper describes a method of rule extraction from trained artificial neural networks. The statem...
Rule extraction from Artificial Neural Networks (ANN's) is an essential step towards the integration...
This last decade multi-layer perceptrons (MLPs) have been widely used in classification tasks. Never...
Artificial neural networks (ANN) have the ability to model input-output relationships from processin...
We propose a mathematical programming methodology for identifying and examining regression rules ext...
Classification and Rule extraction is an important application of Artificial Neural Network. To extr...
神經網路已經被成功地應用於解決各種分類及函數近似的問題，尤其因為神經網路是個萬能的近似器(universal approximator)，所以對於函數近似的問題效果更為顯著。以往對於此類問題雖然多數以...
Two methods of obtaining structured information from a trained feed-forward neural network are discu...
Although backpropagation ANNs generally predict better than decision trees do for pattern classifica...
An important drawback of many artificial neural networks (ANN) is their lack of explanation capabili...
Hybrid intelligent systems that combine knowledge based and artificial neural network systems typica...
In this paper, a learning method for multi-layers neural network in system controller is discussed a...
Despite their success-story, artificial neural networks have one major disadvantage compared to othe...
Search methods for rule extraction from neural networks work by finding those combinations of inputs...
Before symbolic rules are extracted from a trained neural network, the network is usually pruned so ...
This paper describes a method of rule extraction from trained artificial neural networks. The statem...
Rule extraction from Artificial Neural Networks (ANN's) is an essential step towards the integration...
This last decade multi-layer perceptrons (MLPs) have been widely used in classification tasks. Never...
Artificial neural networks (ANN) have the ability to model input-output relationships from processin...