In the last few years, we have witnessed a surge in scholarly interest and scientific evidence of how algorithms can produce discriminatory outcomes, especially with regard to gender and race. However, the analysis of fairness and bias in AI, important for the debate of AI for social good, has paid insufficient attention to the category of age and older people. Ageing populations have been largely neglected during the turn to digitality and AI. In this article, the concept of AI ageism (...) is presented to make a theoretical contribution to how the understanding of inclusion and exclusion within the field of AI can be expanded to include the category of age. AI ageism can be defined as practices and ideologies operating within the field of AI, which exclude, discriminate, or neglect the interests, experiences, and needs of older population and can be manifested in five interconnected forms: (1) age biases in algorithms and datasets (technical level), (2) age stereotypes, prejudices and ideologies of actors in AI (individual level), (3) invisibility of old age in discourses on AI (discourse level), (4) discriminatory effects of use of AI technology on different age groups (group level), (5) exclusion as users of AI technology, services and products (user level). Additionally, the paper provides empirical illustrations of the way ageism operates in these five forms. (shrink)

In this article we introduce the concept of implied optical perspective in deep learning computer vision systems. Taking the BBC's experimental television programme “Made by Machine: When AI met the Archive” as a case study, we trace a conceptual and material link between the system used to automatically “watch” the television archive and a specific type of photographic practice. From a computational aesthetics perspective, we show how deep learning machine vision relies on photography, its technical regimes and epistemic advantages, and (...) we propose a novel way to identify the latent camera through which the BBC archive was seen by machine. (shrink)

In many critical investigations of machine vision, the focus lies almost exclusively on dataset bias and on fixing datasets by introducing more and more diverse sets of images. We propose that machine vision systems are inherently biased not only because they rely on biased datasets but also because theirperceptual topology, their specific way of representing the visual world, gives rise to a new class of bias that we callperceptual bias. Concretely, we define perceptual topology as the set of those inductive (...) biases in machine vision systems that determine its capability to represent the visual world. Perceptual bias, then, describes the difference between the assumed “ways of seeing” of a machine vision system, our reasonable expectations regarding its way of representing the visual world, and its actual perceptual topology. We show how perceptual bias affects the interpretability of machine vision systems in particular, by means of a close reading of a visualization technique called “feature visualization”. We conclude that dataset bias and perceptual bias both need to be considered in the critical analysis of machine vision systems and propose to understand critical machine vision as an important transdisciplinary challenge, situated at the interface of computer science and visual studies/Bildwissenschaft. (shrink)

Modern democratic states are increasingly adopting new information and communication technologies to enhance the efficiency and quality of public administration, public policy and services. However, there is substantial variation in the extent to which countries are successful in pursuing such public digitalization. This paper zooms in on the role of social trust as a possible account for the observed empirical pattern in the range and scope of public digitalization across countries. Our argument is that high social trust makes it easier (...) to digitalize the public sector to the benefit of overall society. We develop a simple game-theoretical model that specifies this positive externality from a high-trust culture and provide empirical evidence that a higher level of social trust is associated with a higher level of public digitalization. Of course, high-trust countries cannot do without the rule of law and some institutionalized mechanisms of control and accountability. However, from our argument, it follows that one future challenge could be that control crowds out trust, so that the balance is no longer optimal. If such overcontrol occurs, public digitalization win–win situations between citizens and government can be undermined, even in high-trust countries. (shrink)

Perceiving and recognizing others via their faces is of pivotal importance. The ability to perceive others in the environment – to discern between friends and foes, selves and others – as well as to detect and seek to predict their possible moves, plans, and intentions, is a set of skills that has proved to be essential in the evolutionary history of humankind. The aim of this study is to explore the subject of face recognition as a semiotic phenomenon. The scope (...) of this inquiry is limited to face perception by the human species. The human face is analysed on the threshold between biological processes and cultural processes. We argue that the recognition of likenesses has a socio-cultural dimension that should not be overlooked. By drawing on Georg Lichtenberg’s remarks on physiognomy, we discuss the critique of the semiotic bias, the association of ideas, and the mechanism of typification involved in face recognition. Face typification is discussed against the background of face recognition and face identification. We take them as three gradients of meaning that map out a network of relationships concerning different cognitive operations that are at stake when dealing with the recognition of faces. (shrink)

Computer vision aims to produce an understanding of digital image’s content and the generation or transformation of images through software. Today, a significant amount of computer vision algorithms rely on techniques of machine learning which require large amounts of data assembled in collections, or named data sets. To build these data sets a large population of precarious workers label and classify photographs around the clock at high speed. For computers to learn how to see, a scale articulates macro and micro (...) dimensions: the millions of images culled from the internet with the few milliseconds given to the workers to perform a task for which they are paid a few cents. This paper engages in details with the production of this scale and the labour it relies on: its elaboration. This elaboration does not only require hands and retinas, it also crucially zes mobilises the photographic apparatus. To understand the specific character of the scale created by computer vision scientists, the paper compares it with a previous enterprise of scaling, Malraux’sLe Musée Imaginaire, where photography was used as a device to undo the boundaries of the museum’s collection and open it to an unlimited access to the world’s visual production. Drawing on Douglas Crimp’s argument that the “musée imaginaire”, a hyperbole of the museum, relied simultaneously on the active role of the photographic apparatus for its existence and on its negation, the paper identifies a similar problem in computer vision’s understanding of photography. The double dismissal of the role played by the workers and the agency of the photographic apparatus in the elaboration of computer vision foreground the inherent fragility of the edifice of machine vision and a necessary rethinking of its scale. (shrink)

During 2018, as part of a research project funded by the Deviant Practice Grant, artist Bruno Moreschi and digital media researcher Gabriel Pereira worked with the Van Abbemuseum collection (Eindhoven, NL), reading their artworks through commercial image-recognition (computer vision) artificial intelligences from leading tech companies. The main takeaways were: somewhat as expected, AI is constructed through a capitalist and product-focused reading of the world (values that are embedded in this sociotechnical system); and that this process of using AI is an (...) innovative way for doing institutional critique, as AI offers an untrained eye that reveals the inner workings of the art system through its glitches. This paper aims to regard these glitches as potentially revealing of the art system, and even poetic at times. We also look at them as a way of revealing the inherent fallibility of the commercial use of AI and machine learning to catalogue the world: it cannot comprehend other ways of knowing about the world, outside the logic of the algorithm. But, at the same time, due to their “glitchy” capacity to level and reimagine, these faulty readings can also serve as a new way of reading art; a new way for thinking critically about the art image in a moment when visual culture has changed form to hybrids of human–machine cognition and “machine-to-machine seeing”. (shrink)

Focused on city-scale automation, and using self-driving cars (SDCs) as a case study, this article reflects on the role of AI—and in particular, computer vision systems used for mapping and navigation—as a catalyst for urban transformation. Urban research commonly presents AI and cities as having a one-way cause-and-effect relationship, giving undue weight to AI’s impact on cities and overlooking the role of cities in shaping AI. Working at the intersection of data science and social research, this paper aims to counter (...) this trend by exploring the reverse perspective: how do cities affect the development, and expose the present limits, of SDCs? The contribution of this paper is threefold. First, by comparing urban and nonurban environments and thoroughly examining the relationship between computer vision and city-specific sociality and form, it defines machine autonomy/automation as a function of the sociotechnical milieu in which an AI system operates. Second, and related, the paper problematizes the notion of SDCs as autonomous technologies and the role it plays in envisioning contending policy arrangements and technical solutions for achieving full driving automation. Finally, the article offers insight into a materialist and spatialized understanding of AI—namely, not as an abstract quality susceptible to replication within discrete machines, but rather as a distributed property emerging through embodied interactions among a multiplicity of agents (human, non-human, and technological) within/with their environments. (shrink)

On February 13, 2020, the Toronto Police Services (TPS) issued a statement admitting that its members had used Clearview AI’s controversial facial recognition technology (FRT). The controversy sparked widespread outcry by the media, civil society, and community groups, and put pressure on policy-makers to address FRTs. Public consultations presented a key tool to contain the scandal in Toronto and across Canada. Drawing on media reports, policy documents, and expert interviews, we investigate four consultations held by the Toronto Police Services Board (...) (TPSB), the Office of the Privacy Commissioner (OPC), and the parliamentary Standing Committee on Access to Information, Privacy and Ethics (ETHI) to understand how public opinion and outrage translate into policy. We find that public consultations became a powerful closure mechanism in the policy-making toolbox, inhibiting rather than furthering democratic debate. Our findings show that consultations do not advance public literacy; that opportunities for public input are narrow; that timeframes are short; and that mechanisms for inclusion are limited. Even in the best-case circumstances, consultations are merely one of many factors in AI governance and seldom impact concrete policy outcomes in the cases studied here. (shrink)

Algorithmic vision, the computational process of making meaning from digital images or visual information, has changed the relationship between the image and the human subject. In this paper, I explicate on the role of algorithmic vision as a technique of algorithmic governance, the organization of a population by algorithmic means. With its roots in the United States post-war cybernetic sciences, the ontological status of the computational image undergoes a shift, giving way to the hegemonic use of automated facial recognition technologies (...) towards predatory policing and profiling practices. By way of example, I argue that algorithmic vision reconfigures the philosophical links between vision, image, and truth, paradigmatically changing the way a human subject is represented through imagistic data. With algorithmic vision, the relationship between subject and representation challenges the humanistic discourse around images, calling for a critical displacement of the human subject from the center of an analysis of how computational images make meaning. I will explore the relationship between the operative image, the image that acts but is not seen by human eyes, and what Louise Amoore calls an “emergent subject,” a subject that is made visible through algorithmic techniques. Algorithmic vision reveals subjects to power in a mode that requires a new approach towards analyzing the entanglement and invisiblization of the human in automated decision-making systems. (shrink)

This article presents Epistemic Spatialization as a new framework for investigating the interconnected patterns of biases when identifying objects with convolutional neural networks. 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 visible, and consign yet others (...) to permanent or haphazard invisibility. Our approach differs from those who focus on high-stakes misidentifications, such as errors tied to structural racism. Examining the far more dominant series of low-stakes mistakes shows the scope of errors, destabilizing the goal of image content identification with considerable societal impact. We explore these issues by closely examining the demonstration video of a popular convnet. This examination reveals an interlocking series of biases undermining the content identification process. The picture we paint is crucial for a better understanding of the errors that result as these convnets become further embedded in everyday products. The framework is valuable for critical work on computer vision, AI studies, and large-scale visual analysis. (shrink)