ALL INTELLIGENCE
OpenAI 官方博客T1·Models

OpenAI Proposes Framework for Interpretable Pedagogical Examples

Original title: Interpretable and pedagogical examples
45AI Score

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.

Full Report

Contents2 sections

Skip to main content

Log inTry ChatGPT(opens in a new window)

Try ChatGPT(opens in a new window)Login

OpenAI

November 2, 2017

Publication

Interpretable and pedagogical examples

Read paper(opens in a new window)

Image 1: Interpretable And Pedagogical Examples

Loading…

Audio 2

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