Jul 2026· Journal of Ambient Intelligence and Humanized Computing· Vol 17, pp. 1647 - 1674· 0 citations· 41 references
TL;DR
A systematic investigation of Bayesian optimization for KANs and its advantages over the most frequently used optimization methods for training neural networks for cardiovascular disease classification on different datasets of varying complexity is presented.
Hyperparameter optimization (HPO) is a critical yet computationally intensive task in modern neural network design, particularly as model architectures and search spaces increase in complexity. Classical methods such as grid search and random search are often inefficient in high-dimensional spaces, while Bayesian optim...
Jacek Tyszkiewicz, Paweł Kolendo, Wojciech Chmiel· International Conference on...· 0 citations
This study presents a new way to tune hyperparameters that is dynamically adaptive, going beyond static methods, and targets challenges in convergence speed, generalization, and model robustness.
Dipti Jaisinghani, V. Joshi· Proceedings of the 1st Inter...· 0 citations
An improved multi-operator differential evolution algorithm, called NN-IMODE, tailored for comprehensive Feedforward Neural Networks optimization, encompassing the number of hidden layers, neurons per layer, weights, biases, and activation functions, is introduced.
Aridj Ferhat, Farouq Zitouni, Karam M. Sallam et al.· Cluster Computing· 0 citations
HYDRA is a parameter-efficient hyperbolic extension of KAN that combines spline-based functional learning with representations in the Poincar\'e ball, and consistently achieves competitive or superior predictive performance while improving parameter efficiency and representation interpretability.
A systematic comparison of backpropagation and ten variants of a genetic algorithm for training multi-layer perceptrons (MLPs), with particular focus on the role of crossover operators, helps clarify when gradient-free training is competitive and which evolutionary operators drive its effectiveness.
Mikołaj Petecki, W. Książek, Artur Niewiarowski· Applied Sciences· 0 citations
Theoretical scaling laws from linear regression to multiclass classification to multiclass classification are extended, while connecting to empirical scaling laws observed in large-scale neural networks.
Konstantinos Christopher Tsiolis, Denny Wu, Christos Thrampoulidis et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
