paper-with-me

Papers

Measuring algorithmic interpretability: A human-learning-based framework and the corresponding cognitive complexity score

2022-05-20 · John P. Lalor, Hong Guo

Algorithmic interpretability is necessary to build trust, ensure fairness, and track accountability. However, there is no existing formal measurement method for algorithmic interpretability. In this work, we build upon programming language theory and cognitive load theory to develop a framework for measuring algorithmic interpretability. The proposed measurement framework reflects the process of a human learning an algorithm. We show that the measurement framework and the resulting cognitive complexity score have the following desirable properties - universality, computability, uniqueness, and monotonicity. We illustrate the measurement framework through a toy example, describe the framework and its conceptual underpinnings, and demonstrate the benefits of the framework, in particular for managers considering tradeoffs when selecting algorithms.

📄 PDF Abstract BibTeX arXiv:2205.10207

Code (0)

등록된 구현이 없습니다.

Tasks

Fairness

Similar Papers 제목 키워드 기반

Algorithmic Insurance

2021-06-01 · Dimitris Bertsimas, Agni Orfanoudaki

As machine learning algorithms start to get integrated into the decision-making process of companies and organizations, insurance products are being developed to protect their owners from liability risk. Algorithmic liab…

Binary ClassificationBreast Cancer DetectionDecision Making

Representation Fidelity:Auditing Algorithmic Decisions About Humans Using Self-Descriptions

2026-03-05 · Theresa Elstner, Martin Potthast arxiv

This paper introduces a new dimension for validating algorithmic decisions about humans by measuring the fidelity of their representations. Representation Fidelity measures if decisions about a person rest on reasonable …

The FairCeptron: A Framework for Measuring Human Perceptions of Algorithmic Fairness

2021-02-08 · Georg Ahnert, Ivan Smirnov, Florian Lemmerich, Claudia Wagner 외

Measures of algorithmic fairness often do not account for human perceptions of fairness that can substantially vary between different sociodemographics and stakeholders. The FairCeptron framework is an approach for study…

Decision MakingFairness

Towards causal benchmarking of bias in face analysis algorithms

2020-07-13 · ECCV 2020 8 · Guha Balakrishnan, Yuanjun Xiong, Wei Xia, Pietro Perona

Measuring algorithmic bias is crucial both to assess algorithmic fairness, and to guide the improvement of algorithms. Current methods to measure algorithmic bias in computer vision, which are based on observational data…

AttributeBenchmarkingFairnessGender Classification

GCI: A (G)raph (C)oncept (I)nterpretation Framework

2023-02-09 · Dmitry Kazhdan, Botty Dimanov, Lucie Charlotte Magister, Pietro Barbiero 외

Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks. An important challenge facing concept extraction approaches …

Explainable Artificial Intelligence (XAI)Molecular Property PredictionPredictionProperty Prediction