The core problem of rule-extraction from feed-forward networks is an inversion problem. In this article, we solve this inversion problem by backpropagating unions of polyhedra. We obtain as a by-product a new rule-extraction technique for which the fidelity of the extracted rules can be made arbitrarily high
In machine learning, ensembles of models based on Multi-Layer Perceptrons (MLPs) or decision trees a...
Knowledge acquisition is, needless to say, important, because it is a key to the solution to one of ...
A novel approach to extract logical rules from data is proposed. Firstly, a structural learning proc...
We propose a mathematical programming methodology for identifying and examining regression rules ext...
Extracting rules from RBFs is not a trivial task because of nonlinear functions or high input dimens...
We describe algorithmic techniques and data structures that have been proposed to solve variants of ...
Although backpropagation ANNs generally predict better than decision trees do for pattern classifica...
Abstract: This paper presents an overview of rule extraction and rule refinement techniques that hav...
Hammer B, Strickert M, Villmann T. Rule Extraction from Self-Organizing Networks. In: Dorronsoro JR,...
An important drawback of many artificial neural networks (ANN) is their lack of explanation capabili...
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 ...
Hybrid intelligent systems that combine knowledge based and artificial neural network systems typica...
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 ...
Extracting rules from RBFs is not a trivial task because of nonlinear functions or high input di-men...
In machine learning, ensembles of models based on Multi-Layer Perceptrons (MLPs) or decision trees a...
Knowledge acquisition is, needless to say, important, because it is a key to the solution to one of ...
A novel approach to extract logical rules from data is proposed. Firstly, a structural learning proc...
We propose a mathematical programming methodology for identifying and examining regression rules ext...
Extracting rules from RBFs is not a trivial task because of nonlinear functions or high input dimens...
We describe algorithmic techniques and data structures that have been proposed to solve variants of ...
Although backpropagation ANNs generally predict better than decision trees do for pattern classifica...
Abstract: This paper presents an overview of rule extraction and rule refinement techniques that hav...
Hammer B, Strickert M, Villmann T. Rule Extraction from Self-Organizing Networks. In: Dorronsoro JR,...
An important drawback of many artificial neural networks (ANN) is their lack of explanation capabili...
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 ...
Hybrid intelligent systems that combine knowledge based and artificial neural network systems typica...
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 ...
Extracting rules from RBFs is not a trivial task because of nonlinear functions or high input di-men...
In machine learning, ensembles of models based on Multi-Layer Perceptrons (MLPs) or decision trees a...
Knowledge acquisition is, needless to say, important, because it is a key to the solution to one of ...
A novel approach to extract logical rules from data is proposed. Firstly, a structural learning proc...
DOI
Add to ORKG