An Evaluation of the Human-Interpretability of Explanation

01/31/2019
by   Isaac Lage, et al.
16

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations interpretable under three specific tasks that users may perform with machine learning systems: simulation of the response, verification of a suggested response, and determining whether the correctness of a suggested response changes under a change to the inputs. Through carefully controlled human-subject experiments, we identify regularizers that can be used to optimize for the interpretability of machine learning systems. Our results show that the type of complexity matters: cognitive chunks (newly defined concepts) affect performance more than variable repetitions, and these trends are consistent across tasks and domains. This suggests that there may exist some common design principles for explanation systems.

READ FULL TEXT
research
02/02/2018

How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation

Recent years have seen a boom in interest in machine learning systems th...
research
02/28/2017

Towards A Rigorous Science of Interpretable Machine Learning

As machine learning systems become ubiquitous, there has been a surge of...
research
06/20/2018

Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems

Several researchers have argued that a machine learning system's interpr...
research
03/09/2020

Explanation-Based Tuning of Opaque Machine Learners with Application to Paper Recommendation

Research in human-centered AI has shown the benefits of machine-learning...
research
04/27/2021

A Human-Centered Interpretability Framework Based on Weight of Evidence

In this paper, we take a human-centered approach to interpretable machin...
research
11/18/2018

Regularized adversarial examples for model interpretability

As machine learning algorithms continue to improve, there is an increasi...
research
08/28/2019

Multi-Objective Automatic Machine Learning with AutoxgboostMC

AutoML systems are currently rising in popularity, as they can build pow...

Please sign up or login with your details

Forgot password? Click here to reset