Relations Between Entropy and Accuracy Trends in Complex Artificial Neural Networks
Book chapter
Authors | Cavallaro, Lucia, Grassia, Marco, Fiumara, Giacomo, Mangioni, Giuseppe, De Meo, Pasquale, Carchiolo, Vincenza, Bagdasar, Ovidiu and Liotta, Antonio |
---|---|
Abstract | Training Artificial Neural Networks (ANNs) is a non-trivial task. In the last years, there has been a growing interest in the academic community in understanding how those structures work and what strategies can be adopted to improve the efficiency of the trained models. Thus, the novel approach proposed in this paper is the inclusion of the entropy metric to analyse the training process. Herein, indeed, an investigation on the accuracy computation process in relation to the entropy of the intra-layers’ weights of multilayer perceptron (MLP) networks is proposed. From the analysis conducted on two well-known datasets with several configurations of the ANNs, we discovered that there is a connection between those two metrics (i.e., accuracy and entropy). These promising results can be helpful in defining, in the future, new criteria to evaluate the training process goodness in real-time by optimising it and allow faster detection of its trend. |
Keywords | Training Artificial Neural Networks; entropy metric; training process |
Year | 2022 |
Book title | Complex Networks & Their Applications X |
Studies in Computational Intelligence | |
Publisher | Springer |
ISSN | 1860-949X |
9783030934125 | |
9783030934132 | |
1860-9503 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-030-93413-2_38 |
Web address (URL) | http://hdl.handle.net/10545/626253 |
https://www.springer.com/tdm | |
hdl:10545/626253 | |
File | File Access Level Open |
File | |
Publication dates | 01 Jan 2022 |
Publication process dates | |
Deposited | 25 Jan 2022, 14:35 |
Accepted | 29 Sep 2021 |
Contributors | University of Derby, Università degli Studi di Catania, Italy, Università degli Studi di Messina, Italy, Polo Universitario Annunziata, Messina, Italy, Università degli Studi di Catania, Catania, Italy and Free University of Bozen-Bolzano, Italy |
https://repository.derby.ac.uk/item/9451w/relations-between-entropy-and-accuracy-trends-in-complex-artificial-neural-networks
Download files
89
total views66
total downloads0
views this month0
downloads this month