M. Tanveer

Region-level learning with granular balls dramatically boosts TSVR's robustness against noise and outliers, outperforming point-wise methods on challenging real-world regression tasks.

IFW-BLS achieves superior robustness against noise and outliers, outperforming traditional models by intelligently down-weighting unreliable samples.

Eliminating backpropagation in physics-informed learning could revolutionize how we solve partial differential equations efficiently.