On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis

1 code implementation • 10 Oct 2023 • Omid Davoodi, Shayan Mohammadizadehsamakosh, Majid Komeili

In this work, we have devised a framework for evaluating the interpretability of part-prototype-based models from a human perspective.

Feature-Based Interpretable Reinforcement Learning based on State-Transition Models

no code implementations • 14 May 2021 • Omid Davoodi, Majid Komeili

In this work, we propose a method for offering local explanations on risk in reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)