Elephant motorbikes and too many neckties: epistemic spatialization as a framework for investigating patterns of bias in convolutional neural networks | SpringerLink

Slider with three content items shown per slide. Use the Previous and Next buttons to navigate the slides or the slide controller buttons at the end to navigate through each slide. Francesco Pierini Xiaoliang Luo, Brett D. Roads & Bradley C. Love Yarden Shir, Naphtali Abudarham & Liad Mudrik Nicolas Malevé Mohammed Bany Muhammad & Mohammed Yeasin AI & SOCIETY (2022)Cite this article 128 Accesses 1 Altmetric Metrics details This article presents Epistemic Spatialization as a new framework for investigating the interconnected patterns of biases when identifying objects with convolutional neural networks (convnets). It draws upon Foucault’s notion of spatialized knowledge to guide its method of enquiry. We argue that decisions involved in the creation of algorithms, alongside the labeling, ordering, presentation, and commercial prioritization of objects, together create a distorted “nomination of the visible”: they harden the visibility of some objects, make other objects excessively visi

Elephant motorbikes and too many neckties: epistemic spatialization as a framework for investigating patterns of bias in convolutional neural networks Open Forum Published: 10 August 2022 Volume 39 , pages 1079–1093 ( 2024 ) Cite this article Save article View saved research AI & SOCIETY Aims and scope Submit manuscript Abstract This article presents Epistemic Spatialization as a new framework for investigating the interconnected patterns of biases when identifying objects with convolutional neural networks (convnets). It draws upon Foucault’s notion of spatialized knowledge to guide its metho

related reading

• Zoom In: An Introduction to Circuitsdistill.pub
• Distill — Latest articles about machine learningdistill.pub
• Feature Visualizationdistill.pub
• Convolutional Neural Networks, Explained | Towards Data Sciencetowardsdatascience.com
• [1811.12231] ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnessarxiv.org
• The “Fraction Sense” Emerges from a Deep Convolutional Neural Networkcognitivesciencesociety.org
• CS231n Deep Learning for Computer Visioncs231n.github.io
• The Building Blocks of Interpretabilitydistill.pub
• The Platonic Representation Hypothesisphillipi.github.io
• Naturally Occurring Equivariance in Neural Networksdistill.pub
• How An Algorithm Feels From Inside — LessWronglesswrong.com
• El automágico traje del emperador | by Bikolabs | bikolabsmedium.com