DeepRED – Rule Extraction from Deep Neural Networks
| Autor: | Eneldo Loza Mencía, Frederik Janssen, Jan Ruben Zilke |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Focus (computing)
Quantitative Biology::Neurons and Cognition Artificial neural network business.industry Computer science Computer Science::Neural and Evolutionary Computation 02 engineering and technology 020204 information systems 0202 electrical engineering electronic engineering information engineering Deep neural networks 020201 artificial intelligence & image processing Split point Artificial intelligence Hidden layer business |
| Zdroj: | Discovery Science ISBN: 9783319463063 DS |
| Popis: | Neural network classifiers are known to be able to learn very accurate models. In the recent past, researchers have even been able to train neural networks with multiple hidden layers (deep neural networks) more effectively and efficiently. However, the major downside of neural networks is that it is not trivial to understand the way how they derive their classification decisions. To solve this problem, there has been research on extracting better understandable rules from neural networks. However, most authors focus on nets with only one single hidden layer. The present paper introduces a new decompositional algorithm – DeepRED – that is able to extract rules from deep neural networks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|