arXiv:2606. 05150v1 Announce Type: cross Abstract: The radial basis function neural network (RBFN) trained with a gradient descending algorithm provides an effective fully connected structure in both shallow and deep networks.
arXiv:2608. 11258v1 Announce Type: new Abstract: Gradient injection helps Particle Swarm Optimization (PSO) only when the swarm has identified a basin with smooth local structure, not universally.
The paper compares genetic algorithm (GA) and gradient descent (GD) training for a distance‑encoding biomorphic‑informational neural network (DEBI‑NN) designed for low‑data medical datasets. A spatial backpropagation scheme was implemented for GD, and both optimizers were evaluated on synthetic, radiomic, and fetal cardiotocography datasets. Across all experiments, GA consistently outperformed GD, achieving higher classification accuracy and more stable decision boundaries, while GD struggled with the interdependent spatial parameters of DEBI‑NN.
arXiv:2607. 11826v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) has automated the design of deep learning models but traditionally requires massive computational resources, often measured in thousands of GPU-days.
arXiv:2606. 02936v1 Announce Type: new Abstract: In this manuscript, we propose and analyze hierarchical Kolmogorov--Arnold neural network architectures employing radial basis functions as activation functions for approximating deterministic functions and random field models.
arXiv:2607. 19031v1 Announce Type: new Abstract: Automated algorithm selection in black-box optimization typically relies on supervised models that map landscape features to algorithm performance labels.
arXiv:2609.22329v1 Announce Type: cross Abstract: Black-Box Optimization (BBO) is often applied in several engineering fields and can utilize an advancement of numerical measure- ments and simulation...
This paper proposes a particle‑swarm‑assisted gradient meta‑learning (PSA‑GML) algorithm to jointly optimize the transmit precoder and the transmission/reflection coefficients of a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR‑RIS) for maximizing weighted sum rate in a multi‑user downlink. The method first transforms the non‑convex problem via amplitude‑split parameterization and collapsed precoder representation, then uses particle swarm optimization to generate a robust warm start for the STAR‑RIS coefficients, and finally refines both coefficients and precoder with a coordinate‑wise LSTM meta‑optimizer trained by first‑order gradient meta‑learning. Numerical results demonstrate that PSA‑GML achieves an 11.06 bits/s/Hz weighted sum rate at 10 dB, outperforming conventional alternating optimization by 13.1 % and the random‑phase scheme by 35.1 %, while also showing strong zero‑shot transfer across regimes.
arXiv:2609.24401v1 Announce Type: new Abstract: Structured pruning is a model compression technique that is used to reduce the computational cost of deploying deep neural networks on resource-constra...
This paper investigates the joint optimization of the transmit precoder and the transmission/reflection coefficients of a simultaneously transmitting and reflecting reconfigurable intelligent surface...
arXiv:2501.18018v2 Announce Type: replace-cross Abstract: The neurons of artificial neural networks were originally invented when much less was known about biological neurons than is known today. Our...
arXiv:2608. 14472v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) aims to automate neural network architecture design, reducing reliance on human expertise.
arXiv:2606. 04039v1 Announce Type: cross Abstract: Neural-guided Ant Colony Optimization (ACO) suffers from a fundamental training-inference misalignment: policies are typically trained to generate static priors (e.