**摘要**
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. The error correction (ErrCor), a state-of-the-art gradient-based training method, selects optimal hidden units to improve accuracy. Alternatively, as a population-based algorithm, the particle swarm optimization algorithm (P
👤 作者: Ammar Hoori, Yuichi Motai

---
🔗 **[Multi-Column RBF Neural Network Using Adaptive and Non-Adaptive Particle Swarm Optimization](https://arxiv.org/abs/2606.05150v1)**

> Multi-Column RBF Neural Network Using Adaptive and Non-Adaptive Particle Swarm Optimization
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-04 14:01