LICON
Autor: | Gjergji Kasneci, Thomas Gottron |
---|---|
Rok vydání: | 2016 |
Předmět: |
Scheme (programming language)
Artificial neural network Computer science business.industry Time delay neural network Linear model 02 engineering and technology Logistic regression Machine learning computer.software_genre Weighting Variable (computer science) 020204 information systems Pattern recognition (psychology) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer computer.programming_language |
Zdroj: | CIKM |
Popis: | In recent years artificial neural networks have become the method of choice for many pattern recognition tasks. Despite their overwhelming success, a rigorous and easy to interpret mathematical explanation of the influence of input variables on a output produced by a neural network is still missing. We propose a generic framework as well as a concrete method for quantifying the influence of individual input signals on the output computed by a deep neural network. Inspired by the variable weighting scheme in the log-linear combination of variables in logistic regression, the proposed method provides linear models for specific observations of the input variables. This linear model locally approximates the behaviour of the neural network and can be used to quantify the influence of input variables in a principled way. We demonstrate the effectiveness of the proposed method in experiments on various synthetic and real-world datasets. |
Databáze: | OpenAIRE |
Externí odkaz: |