randomized-neural-networks

The paper proposes intuitionistic fuzzy deep RVFL (IF-dRVFL) and ensemble deep RVFL (IF-edRVFL) frameworks that use sample neighborhood information to improve robustness against noise and outliers in classification tasks, outperforming existing SOTA fuzzy and non-fuzzy approaches on benchmark datasets.

介绍CAWI，一种基于Copula的随机神经网络权重初始化方法，该方法建模特征间依赖关系，在83个分类基准上提升了预测性能。