Extension to Multidimensional Problems of a Fuzzy-Based Explainable and Noise-Resilient Algorithm

Abstract

While Deep Neural Networks (DNNs) have shown incredible performance in a variety of data, they are brittle and opaque: easily fooled by the presence of noise, and difficult to understand the underlying reasoning for their predictions or choices. This focus on accuracy at the expense of interpretability and robustness caused little concern since, until recently, DNNs were employed primarily for scientific and limited commercial work. An increasing, widespread use of artificial intelligence and growing emphasis on user data protections, however, motivates the need for robust solutions with explainable methods and results. In this work, we extend a novel fuzzy based algorithm for regression to multidimensional problems. Previous research demonstrated that this approach outperforms neural network benchmarks while using only 5% of the number of the parameters.