OpenAI Proposes Framework for Interpretable Pedagogical Examples
OpenAI researchers propose a framework where a 'teacher network' generates interpretable and pedagogically valuable examples to help humans understand complex concepts like rules, probabilities, and hierarchies. The study demonstrates how neural networks can actively select or construct the most informative samples to facilitate human learning.
Related Entities
Full Report
Contents2 sections
Log inTry ChatGPT(opens in a new window)
- Research
- Products
- Business
- Developers
- Company
- Foundation(opens in a new window)
Try ChatGPT(opens in a new window)Login
OpenAI
November 2, 2017
Interpretable and pedagogical examples
Read paper(opens in a new window)

Loading…
Share
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.
Authors
Smitha Milli, Pieter Abbeel, Igor Mordatch