This repository houses a set of functions dedicated to the study of how well neural networks can learn a piecewise function dataset of varying complexity. You will find code dedicated to generating ...

In this paper, we propose a method for finding the best piecewise linearization of nonlinear functions. For this aim, we try to obtain the best approximation of a nonlinear function as a piecewise ...

Abstract: This letter considers the problem of piecewise affine abstraction with polytopic partitions of nonlinear systems, i.e., the over-approximation of nonlinear dynamics by a pair of piecewise ...

A python implementation of the algorithm used to generate optimal piecewise linear approximations of convex functions proposed by Imamoto and Tang [1]. The algorithm uses an iterative search to find ...

Abstract: One of the most important properties of neural nets (NNs) for control purposes is the universal approximation property. Unfortunately,, this property is generally proven for continuous ...

Humans are capable of learning a new fine-grained concept with very little supervision, e.g., few exemplary images for a species of bird, yet our best deep learning systems need hundreds or thousands ...

Dose-response meta-analysis (DRMA) is widely employed to establishing the potential dose-response relationship between continuous exposures and disease outcomes. However, no method is readily ...