Title
Artificial Neural Networks with a Signed-Rank Objective Function and Applications
Document Type
Article
Publication Date
2022
Abstract
In this paper, we propose to analyze artificial neural networks using a signed-rank objective function as the error function. We prove that the variance of the gradient of the learning process is bounded as a function of the number of patterns and/or outputs, therefore preventing the gradient explosion phenomenon. Simulations show that the method is particularly efficient at reproducing chaotic behaviors from biological models such as the Logistic and Ricker models. In particular, the accuracy of the learning process is improved relatively to the least squares objective function in these cases. Applications in regression settings on two real datasets, one small and the other relatively large are also considered.
DOI
10.1080/03610918.2020.1714659
Publisher
Taylor & Francis
Repository Citation
Kwessi, E., & Edwards, L. J. (2022). Artificial neural networks with a signed-rank objective function and applications. Communications in Statistics - Simulation and Computation, 51(6), 3363-3388. http://doi.org/10.1080/03610918.2020.1714659
Publication Information
Communications in Statistics - Simulation and Computation