Oleksander Barmak

You are already at the latest version Deep learning architectures produce highly effective yet uninterpretable latent representations, creating an interpretability gap that fundamentally impairs model verification and automated rule extraction. In this work, we propose Global Semantic Transition (SEMTRA), a post-hoc framework bridging this gap by translating numerical representations into auditable rough-set production rules without retraining the underlying feature extractor.

This version is not peer-reviewed. Vitaliy Pavlyshyn,Eduard Manziuk,Oleksander Barmak,Pavlo Radiuk  *,Iurii Krak Vitaliy Pavlyshyn,Eduard Manziuk,Oleksander Barmak,Pavlo Radiuk  *,Iurii Krak This version is not peer-reviewed. Inefficiencies in urban traffic management, particularly from static traffic light regulation, pose significant challenges to optimizing traffic flows and mitigating environmental impact.