Increasing biases can be more efficient than increasing weights

Carlo Metta, Marco Fantozzi, Andrea Papini, Gianluca Amato, Matteo Bergamaschi, Andrea Fois, Silvia Giulia Galfrè, Alessandro Marchetti, Michelangelo Vegliò, Maurizio Parton () and Francesco Morandin
Additional contact information
Carlo Metta: ISTI-CNR
Marco Fantozzi: University of Parma
Andrea Papini: Scuola Normale Superiore
Gianluca Amato: University of Chieti-Pescara
Matteo Bergamaschi: University of Padova
Andrea Fois: University of Parma
Silvia Giulia Galfrè: University of Pisa
Alessandro Marchetti: University of Chieti-Pescara
Michelangelo Vegliò: University of Chieti-Pescara
Maurizio Parton: University of Chieti-Pescara
Francesco Morandin: University of Parma

Advances in Data Analysis and Classification, 2025, vol. 19, issue 2, No 6, 437-468

Abstract: Abstract We introduce a novel computational unit for neural networks that features multiple biases, challenging the traditional perceptron structure. This unit emphasizes the importance of preserving uncorrupted information as it is passed from one unit to the next, applying activation functions later in the process with specialized biases for each unit. Through both empirical and theoretical analyses, we show that by focusing on increasing biases rather than weights, there is potential for significant enhancement in a neural network model’s performance. This approach offers an alternative perspective on optimizing information flow within neural networks. See source code (CurioSAI in Increasing biases can be more efficient than increasing weights, 2023. https://github.com/CuriosAI/dac-dev ).

Keywords: CLADAG 2023 SPECIAL ISSUE; Computational unit; Preactivation; Multi-bias; Active dendrite; 68T07; 92B20 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11634-025-00649-2 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:advdac:v:19:y:2025:i:2:d:10.1007_s11634-025-00649-2

Ordering information: This journal article can be ordered from
http://www.springer. ... ds/journal/11634/PS2

DOI: 10.1007/s11634-025-00649-2

Access Statistics for this article

Advances in Data Analysis and Classification is currently edited by H.-H. Bock, W. Gaul, A. Okada, M. Vichi and C. Weihs

More articles in Advances in Data Analysis and Classification from Springer, German Classification Society - Gesellschaft für Klassifikation (GfKl), Japanese Classification Society (JCS), Classification and Data Analysis Group of the Italian Statistical Society (CLADAG), International Federation of Classification Societies (IFCS)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().