NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks

In this work, we formulate Newron:a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neurons. We show that some specializations of Newronallow the network to be interpretable without affecting their expressiveness. We can understand the rules governing the task by just inspecting the models produced by our Newnon-based networks. Extensive experiments show that the quality of the generated models is better than traditional interpretable models and in line or better than standard neural networks.