[Nov 22nd 2021] LabMeeting: NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks

Maria Sofia Bucarelli (University of Rome)

When: Nov 22nd, 2021 – 11:00 – 11:45 AM
Where: Google meet link

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 in line with standard neural network models (in collaboration with Federico Siciliano, Gabriele Tolomei and Fabrizio Silvestri).

 |  Category: Seminars