Deep neural networks are said to be opaque, impeding the development of safe and trustworthy artificial intelligence, but where this opacity stems from is less clear. What are the sufficient properties for neural network opacity? Here, I discuss five common properties of deep neural networks and two different kinds of opacity. Which of these properties are sufficient for what type of opacity? I show how each kind of opacity stems from only one of these five properties, and then discuss to (...) what extent the two kinds of opacity can be mitigated by explainability methods. (shrink)

For synergistic interactions between humans and artificial intelligence (AI) systems, AI outputs often need to be explainable to people. Explainable AI (XAI) systems are commonly tested in human user studies. However, whether XAI researchers consider potential cultural differences in human explanatory needs remains unexplored. We highlight psychological research that found significant differences in human explanations between many people from Western, commonly individualist countries and people from non-Western, often collectivist countries. We argue that XAI research currently overlooks these variations and that (...) many popular XAI designs implicitly and problematically assume that Western explanatory needs are shared cross-culturally. Additionally, we systematically reviewed over 200 XAI user studies and found that most studies did not consider relevant cultural variations, sampled only Western populations, but drew conclusions about human-XAI interactions more generally. We also analyzed over 30 literature reviews of XAI studies. Most reviews did not mention cultural differences in explanatory needs or flag overly broad cross-cultural extrapolations of XAI user study results. Combined, our analyses provide evidence of a cultural bias toward Western populations in XAI research, highlighting an important knowledge gap regarding how culturally diverse users may respond to widely used XAI systems that future work can and should address. (shrink)

The increasing demand for transparency in AI has recently come under scrutiny. The question is often posted in terms of “epistemic double standards”, and whether the standards for transparency in AI ought to be higher than, or equivalent to, our standards for ordinary human reasoners. I agree that the push for increased transparency in AI deserves closer examination, and that comparing these standards to our standards of transparency for other opaque systems is an appropriate starting point. I suggest that a (...) more fruitful exploration of this question will involve a different comparison class. We routinely treat judgments made by highly trained experts in specialized fields as fair or well-grounded even though—by the nature of expert/layperson division of epistemic labor—an expert will not be able to provide an explanation of the reasoning behind these judgments that makes sense to most other people. Regardless, laypeople are thought to be acting reasonably—and ethically—in deferring to the judgments of experts that concern their areas of specialization. I suggest that we reframe our question regarding the appropriate standards of transparency in AI as one that asks when, why, and to what degree it would be ethical to accept opacity in AI. I argue that our epistemic relation to certain opaque AI technology may be relevantly similar to the layperson’s epistemic relation to the expert in certain respects, such that the successful expert/layperson division of epistemic labor can serve as a blueprint for the ethical use of opaque AI. (shrink)

The philosophical debate around the impact of machine learning in science is often framed in terms of a choice between AI and classical methods as mutually exclusive alternatives involving difficult epistemological trade-offs. A common worry regarding machine learning methods specifically is that they lead to opaque models that make predictions but do not lead to explanation or understanding. Focusing on the field of molecular biology, I argue that in practice machine learning is often used with explanatory aims. More specifically, I (...) argue that machine learning can be tightly integrated with other, more traditional, research methods and in a clear sense can contribute to insight into the causal processes underlying phenomena of interest to biologists. One could even say that machine learning is not the end of theory in important areas of biology, as has been argued, but rather a new beginning. I support these claims with a detailed discussion of a case study involving gene regulation by microRNAs. (shrink)

The ongoing explosion of interest in artificial intelligence is fueled in part by recently developed techniques in machine learning. Those techniques allow automated systems to process huge amounts of data, utilizing mathematical methods that depart from traditional statistical approaches, and resulting in impressive advancements in our ability to make predictions and uncover correlations across a host of interesting domains. But as is now widely discussed, the way that those systems arrive at their outputs is often opaque, even to the experts (...) who design and deploy them. Is it morally problematic to make use of opaque automated methods when making high-stakes decisions, like whether to issue a loan to an applicant, or whether to approve a parole request? Many scholars answer in the affirmative. However, there is no widely accepted explanation for why transparent systems are morally preferable to opaque systems. We argue that the use of automated decision-making systems sometimes violates duties of consideration that are owed by decision-makers to decision-subjects, duties that are both epistemic and practical in character. Violations of that kind generate a weighty consideration against the use of opaque decision systems. In the course of defending our approach, we show that it is able to address three major challenges sometimes leveled against attempts to defend the moral import of transparency in automated decision-making. (shrink)

The contention that medical artificial intelligence (AI) should be ‘explainable’ is widespread in contemporary philosophy and in legal and best practice documents. Yet critics argue that ‘explainability’ is not a stable concept; non-explainable AI is often more accurate; mechanisms intended to improve explainability do not improve understanding and introduce new epistemic concerns; and explainability requirements are ad hoc where human medical decision-making is often opaque. A recent ‘political response’ to these issues contends that AI used in high-stakes scenarios, including medical (...) AI, must be explainable to meet basic standards of legitimacy: People are owed reasons for decisions that impact their vital interests, and this requires explainable AI. This article demonstrates why the political response fails. Attending to systemic considerations, as its proponents desire, suggests that the political response is subject to the same criticisms as other arguments for explainable AI and presents new issues. It also suggests that decision-making about non-explainable medical AI can meet public reason standards. The most plausible version of the response amounts to a simple claim that public reason demands reasons why AI is permitted. But that does not actually support explainable AI or respond to criticisms of strong requirements for explainable medical AI. (shrink)

There is a deluge of AI-assisted decision-making systems, where our data serve as proxy to our actions, suggested by AI. The closer we investigate our data (raw input, or their learned representations, or the suggested actions), we begin to discover “bugs”. Outside of their test, controlled environments, AI systems may encounter situations investigated primarily by those in other disciplines, but experts in those fields are typically excluded from the design process and are only invited to attest to the ethical features (...) of the resulting system or to comment on demonstrations of intelligence and aspects of craftmanship after the fact. This communicative impasse must be overcome. Our idea is that philosophical and engineering considerations interact and can be fruitfully combined in the AI design process from the very beginning. We embody this idea in the role of a philosopher engineer. We discuss the role of philosopher engineers in the three main design stages of an AI system: deployment management (what is the system’s intended use, in what environment?); objective setting (what should the system be trained to do, and how?); and training (what model should be used, and why?). We then exemplify the need for philosopher engineers with an illustrative example, investigating how the future decisions of an AI-based hiring system can be fairer than those contained in the biased input data on which it is trained; and we briefly sketch the kind of interdisciplinary education that we envision will help to bring about better AI. (shrink)