Pages that link to "Item:Q3123293"

The following pages link to Extracting Rules from Neural Networks by Pruning and Hidden-Unit Splitting (Q3123293):

Displaying 17 items.

• Generating rules with predicates, terms and variables from the pruned neural networks (Q280332) (← links)
• The upper bound of the minimal number of hidden neurons for the parity problem in binary neural networks (Q439836) (← links)
• Neural network explanation using inversion (Q866739) (← links)
• A note on knowledge discovery using neural networks and its application to credit card screening (Q948676) (← links)
• A hybrid approach to design efficient learning classifiers (Q980088) (← links)
• Rule extraction from local cluster neural nets (Q1851910) (← links)
• Extract intelligible and concise fuzzy rules from neural networks (Q1867676) (← links)
• Is it worth generating rules from neural network ensembles? (Q1884273) (← links)
• Extracting Boolean and probabilistic rules from trained neural networks (Q1980413) (← links)
• Modular representation of layered neural networks (Q2179094) (← links)
• A Penalty-Function Approach for Pruning Feedforward Neural Networks (Q3123292) (← links)
• Piecewise-Linear Neural Networks and Their Relationship to Rule Extraction from Data (Q3413093) (← links)
• Quo Vadis? Reliable and Practical Rule Extraction from Neural Networks (Q5305709) (← links)
• (Q5389820) (← links)
• Advances in Neural Networks – ISNN 2005 (Q5706969) (← links)
• Symbolic knowledge extraction from trained neural networks: A sound approach (Q5940782) (← links)
• Extracting and inserting knowledge into stacked denoising auto-encoders (Q6078688) (← links)