Squashing activation functions in benchmark tests: Towards a more eXplainable Artificial Intelligence using continuous-valued logic.
Daniel ZeltnerBenedikt SchmidGábor CsiszárOrsolya CsiszárPublished in: Knowl. Based Syst. (2021)
Keyphrases
- benchmark tests
- activation function
- artificial intelligence
- valued logic
- continuous functions
- neural network
- feed forward
- fuzzy logic
- artificial neural networks
- back propagation
- complex valued
- classical logic
- neural nets
- propositional logic
- hidden layer
- learning rate
- expert systems
- radial basis function
- multi layer perceptron
- fuzzy sets
- multilayer perceptron
- first order logic
- multi valued
- fuzzy neural network
- computational intelligence
- truth values
- bayesian networks
- machine learning