Interpretable and Pedagogical Examples
arXiv:1711.00694
Abstract
Teachers intentionally pick the most informative examples to show their students. However, if the teacher and student are neural networks, the examples that the teacher network learns to give, although effective at teaching the student, are typically uninterpretable. We show that training the student and teacher iteratively, rather than jointly, can produce interpretable teaching strategies. We evaluate interpretability by (1) measuring the similarity of the teacher's emergent strategies to intuitive strategies in each domain and (2) conducting human experiments to evaluate how effective the teacher's strategies are at teaching humans. We show that the teacher network learns to select or generate interpretable, pedagogical examples to teach rule-based, probabilistic, boolean, and hierarchical concepts.
References in corpus (5)
- Categorical Reparameterization with Gumbel-Softmax
- Towards A Rigorous Science of Interpretable Machine Learning
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
- Proceedings of NIPS 2017 Symposium on Interpretable Machine Learning
Cited by in corpus (6)
- AI safety via debate
- Unexplainability and Incomprehensibility of Artificial Intelligence
- Interactive Reinforcement Learning for Object Grounding via Self-Talking
- Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
- The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems
- Accelerating Entrepreneurial Decision-Making Through Hybrid Intelligence