Understanding Neural Networks via Rule Extraction
نویسندگان
چکیده
Although backpropagation neural networks generally predict better than decision trees do for pattern classi cation problems they are of ten regarded as black boxes i e their predic tions are not as interpretable as those of deci sion trees This paper argues that this is be cause there has been no proper technique that enables us to do so With an algorithm that can extract rules by drawing parallels with those of decision trees we show that the predic tions of a network can be explained via rules ex tracted from it thereby the network can be un derstood Experiments demonstrate that rules extracted from neural networks are compara ble with those of decision trees in terms of pre dictive accuracy number of rules and average number of conditions for a rule they preserve high predictive accuracy of original networks
منابع مشابه
Knowledge Extraction from the Neural ‘Black Box’ in Ecological Monitoring
Phytoplankton biomass within the Saginaw Bay ecosystem (Lake Huron, Michigan, USA) was characterized as a function of select physical/chemical indicators. The complexity and variability of ecological systems typically make it difficult to model the influences of anthropogenic stressors and/or natural disturbances. Here, Artificial Neural Networks (ANNs) were developed to model chlorophyll a con...
متن کاملFuzzy Apriori Rule Extraction Using Multi-Objective Particle Swarm Optimization: The Case of Credit Scoring
There are many methods introduced to solve the credit scoring problem such as support vector machines, neural networks and rule based classifiers. Rule bases are more favourite in credit decision making because of their ability to explicitly distinguish between good and bad applicants.In this paper multi-objective particle swarm is applied to optimize fuzzy apriori rule base in credit scoring. ...
متن کاملFuzzy Apriori Rule Extraction Using Multi-Objective Particle Swarm Optimization: The Case of Credit Scoring
There are many methods introduced to solve the credit scoring problem such as support vector machines, neural networks and rule based classifiers. Rule bases are more favourite in credit decision making because of their ability to explicitly distinguish between good and bad applicants.In this paper multi-objective particle swarm is applied to optimize fuzzy apriori rule base in credit scoring. ...
متن کاملINTEGRATED ADAPTIVE FUZZY CLUSTERING (IAFC) NEURAL NETWORKS USING FUZZY LEARNING RULES
The proposed IAFC neural networks have both stability and plasticity because theyuse a control structure similar to that of the ART-1(Adaptive Resonance Theory) neural network.The unsupervised IAFC neural network is the unsupervised neural network which uses the fuzzyleaky learning rule. This fuzzy leaky learning rule controls the updating amounts by fuzzymembership values. The supervised IAFC ...
متن کاملUsing Sampling and Queries to Extract Rules fromTrained Neural
Concepts learned by neural networks are dif-cult to understand because they are represented using large assemblages of real-valued parameters. One approach to understanding trained neural networks is to extract symbolic rules that describe their classiica-tion behavior. There are several existing rule-extraction approaches that operate by searching for such rules. We present a novel method that...
متن کامل