Two Instances of Interpretable Neural Network for Universal Approximations
Machine Learning
2022-05-10 v2 Artificial Intelligence
Abstract
This paper proposes two bottom-up interpretable neural network (NN) constructions for universal approximation, namely Triangularly-constructed NN (TNN) and Semi-Quantized Activation NN (SQANN). Further notable properties are (1) resistance to catastrophic forgetting (2) existence of proof for arbitrarily high accuracies (3) the ability to identify samples that are out-of-distribution through interpretable activation "fingerprints".
Keywords
Cite
@article{arxiv.2112.15026,
title = {Two Instances of Interpretable Neural Network for Universal Approximations},
author = {Erico Tjoa and Guan Cuntai},
journal= {arXiv preprint arXiv:2112.15026},
year = {2022}
}