Arguing Machines: Human Supervision of Black Box AI Systems That Make Life-Critical Decisions
We consider the paradigm of a black box AI system that makes life-critical decisions. We propose an "arguing machines" framework that pairs the primary AI system with a secondary one that is independently trained to perform the same task. We show that disagreement between the two systems, without any knowledge of underlying system design or operation, is sufficient to arbitrarily improve the accuracy of the overall decision pipeline given human supervision over disagreements. We demonstrate this system in two applications: (1) an illustrative example of image classification and (2) on large-scale real-world semi-autonomous driving data. For the first application, we apply this framework to image classification achieving a reduction from 8.0% to 2.8% top-5 error on ImageNet. For the second application, we apply this framework to Tesla Autopilot and demonstrate the ability to predict 90.4% of system disengagements that were labeled by human annotators as challenging and needing human supervision.
Code (1)
Tasks
Autonomous DrivingGeneral Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Conscious Intelligence Requires Lifelong Autonomous Programming For General Purposes
Universal Turing Machines [29, 10, 18] are well known in computer science but they are about manual programming for general purposes. Although human children perform conscious learning (i.e., learning while being conscio…
Natural Language UnderstandingRobust Deep Learning Control with Guaranteed Performance for Safe and Reliable Robotization in Heavy-Duty Machinery
Today's heavy-duty mobile machines (HDMMs) face two transitions: from diesel-hydraulic actuation to clean electric systems driven by climate goals, and from human supervision toward greater autonomy. Diesel-hydraulic sys…
Language Models as Semiotic Machines: Reconceptualizing AI Language Systems through Structuralist and Post-Structuralist Theories of Language
This paper proposes a novel framework for understanding large language models (LLMs) by reconceptualizing them as semiotic machines rather than as imitations of human cognition. Drawing from structuralist and post-struct…
Overview of Class Activation Maps for Visualization Explainability
Recent research in deep learning methodology has led to a variety of complex modelling techniques in computer vision (CV) that reach or even outperform human performance. Although these black-box deep learning models hav…
Decision MakingDeep LearningHuman-Machine Comparison for Cross-Race Face Verification: Race Bias at the Upper Limits of Performance?
Face recognition algorithms perform more accurately than humans in some cases, though humans and machines both show race-based accuracy differences. As algorithms continue to improve, it is important to continually asses…
Face RecognitionFace Verification