A parameterized activation function for learning fuzzy logic operations in deep neural networks
This work addresses the challenge of integrating fuzzy logic into deep learning for interpretability, though it appears incremental as it builds on existing activation function concepts.
The authors tackled the problem of learning fuzzy logic expressions by introducing a parameterized, differentiable activation function that enables neural networks to learn logical operations via gradient descent, and they demonstrated its effectiveness on five UCI classification tasks.
We present a deep learning architecture for learning fuzzy logic expressions. Our model uses an innovative, parameterized, differentiable activation function that can learn a number of logical operations by gradient descent. This activation function allows a neural network to determine the relationships between its input variables and provides insight into the logical significance of learned network parameters. We provide a theoretical basis for this parameterization and demonstrate its effectiveness and utility by successfully applying our model to five classification problems from the UCI Machine Learning Repository.