3 papers
cs.CL2026
Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation
Ashish Rana, Chia-Chien Hung, Qumeng Sun +2
Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues. In contrast, memory-augme…
cs.LG2026
Prototype-Based Learning for Healthcare: A Demonstration of Interpretable AI
Ashish Rana, Ammar Shaker, Sascha Saralajew +6
Despite recent advances in machine learning and explainable AI, a gap remains in personalized preventive healthcare: predictions, interventions, and recommendations should be both…
cs.LG2024
A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations
Sascha Saralajew, Ashish Rana, Thomas Villmann +1
Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as low…