NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks
This work addresses the problem of interpretability in neural networks for researchers and practitioners, offering a novel framework that is incremental in its approach.
The authors introduced NEWRON, a generalization of the artificial neuron designed to enhance neural network interpretability without compromising expressiveness, achieving model quality comparable to or better than standard neural networks in experiments.
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 NEWRON allow the network to be interpretable with no change in their expressiveness. By just inspecting the models produced by our NEWRON-based networks, we can understand the rules governing the task. 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.