5 papers
LLN: Learnable Lens Networks for Parameter-Efficient Long-Horizon Dynamical Prediction
Binbin Yong, Zhao Su, Lan Guo +3
Explicit residual connections of the form (x+f(x)), often combined with normalization layers, have become a standard strategy for training very deep neural networks. However, resid…
Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
Lan Guo, Jie Xiao, Zhao Su +5
In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states, while existing deep forecasting models usually compre…
HYDRA: Hyperbolic Dynamic Representation Architecture for Kolmogorov-Arnold Networks
Zhao Su, Yuxin Xia, Haoran Li +4
Kolmogorov-Arnold Networks (KANs) enhance nonlinear function approximation by replacing scalar weights with learnable univariate functions. However, assigning an independent functi…
HyperANFIS: Enhancing Rule Representation and Interpretability in Adaptive Neuro-Fuzzy Systems via Hyperbolic Geometry
Haoran Pei, Zhao Su, Zetao Lin +6
The adaptive neuro-fuzzy inference system (ANFIS) is an interpretable reasoning framework capable of generating explicit IF-THEN fuzzy rules, making it suitable for tasks requiring…
KANFIS: A Neuro-Symbolic Framework for Interpretable and Uncertainty-Aware Learning
Binbin Yong, Haoran Pei, Jun Shen +3
Adaptive Neuro-Fuzzy Inference System (ANFIS) was designed to combine the learning capabilities of neural network with the reasoning transparency of fuzzy logic. However, conventio…