2 papers
cs.LG2025
REAct: Rational Exponential Activation for Better Learning and Generalization in PINNs
Sourav Mishra, Shreya Hallikeri, Suresh Sundaram
Physics-Informed Neural Networks (PINNs) offer a promising approach to simulating physical systems. Still, their application is limited by optimization challenges, mainly due to th…
cs.LG2024
Towards Improved Imbalance Robustness in Continual Multi-Label Learning with Dual Output Spiking Architecture (DOSA)
Sourav Mishra, Shirin Dora, Suresh Sundaram
Algorithms designed for addressing typical supervised classification problems can only learn from a fixed set of samples and labels, making them unsuitable for the real world, wher…