Scalable Partial Explainability in Neural Networks via Flexible Activation Functions (Student Abstract)

Current state-of-the-art neural network explanation methods (e.g. Saliency maps, DeepLIFT, LIME, etc.) focus more on the direct relationship between NN outputs and inputs rather than the NN structure and operations itself, hence there still exists uncertainty over the exact role played by neurons. In this paper, we propose a novel neural network structure with Kolmogorov-Arnold Superposition Theorem based topology and Gaussian Processes based flexible activation function to achieve partial explainability of the neuron inner reasoning. The model feasibility is verified in a case study on binary classification of the banknotes.