Abstract:This paper extends and explains the Multiple Additive Neural Networks (MANN) methodology, an enhancement to the traditional Gradient Boosting framework, utilizing nearly shallow neural networks instead of decision trees as base learners. This innovative approach leverages neural network architectures, notably Convolutional Neural Networks (CNNs) and Capsule Neural Networks, to extend its application to both structured data and unstructured data such as images and audio. For structured data the advantages of capsule neural networks as feature extractors are used and combined with MANN as a classifier. MANN's unique architecture promotes continuous learning and integrates advanced heuristics to combat overfitting, ensuring robustness and reducing sensitivity to hyperparameter settings like learning rate and iterations. Our empirical studies reveal that MANN surpasses traditional methods such as Extreme Gradient Boosting (XGB) in accuracy across well-known datasets. This research demonstrates MANN's superior precision and generalizability, making it a versatile tool for diverse data types and complex learning environments.
| Comments: | Accepted author manuscript; page layout differs from the published Springer version |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.26888 [cs.LG] |
| (or arXiv:2604.26888v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26888 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | In: Bäck, T. et al. (eds.), Computational Intelligence, IJCCI 2023, Studies in Computational Intelligence, vol. 1196, Springer, Cham, pp. 165-186 (2025) |
| Related DOI: | https://doi.org/10.1007/978-3-031-85252-7_10
DOI(s) linking to related resources |
Submission history
From: Jörg Frochte [view email]
[v1]
Wed, 29 Apr 2026 16:57:40 UTC (1,008 KB)
