We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealised explanation game in which players collaborate to find the best explanation for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal (...) patterns of variable granularity and scope. We characterise the conditions under which such a game is almost surely guaranteed to converge on a optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions. (shrink)

Machine learning algorithms may radically improve our ability to diagnose and treat disease. For moral, legal, and scientific reasons, it is essential that doctors and patients be able to understand and explain the predictions of these models. Scalable, customisable, and ethical solutions can be achieved by working together with relevant stakeholders, including patients, data scientists, and policy makers.

Artificial intelligence has historically been conceptualized in anthropomorphic terms. Some algorithms deploy biomimetic designs in a deliberate attempt to effect a sort of digital isomorphism of the human brain. Others leverage more general learning strategies that happen to coincide with popular theories of cognitive science and social epistemology. In this paper, I challenge the anthropomorphic credentials of the neural network algorithm, whose similarities to human cognition I argue are vastly overstated and narrowly construed. I submit that three alternative supervised learning (...) methods—namely lasso penalties, bagging, and boosting—offer subtler, more interesting analogies to human reasoning as both an individual and a social phenomenon. Despite the temptation to fall back on anthropomorphic tropes when discussing AI, however, I conclude that such rhetoric is at best misleading and at worst downright dangerous. The impulse to humanize algorithms is an obstacle to properly conceptualizing the ethical challenges posed by emerging technologies. (shrink)

Recent years have seen a surge in online collaboration between experts and amateurs on scientific research. In this article, we analyse the epistemological implications of these crowdsourced projects, with a focus on Zooniverse, the world’s largest citizen science web portal. We use quantitative methods to evaluate the platform’s success in producing large volumes of observation statements and high impact scientific discoveries relative to more conventional means of data processing. Through empirical evidence, Bayesian reasoning, and conceptual analysis, we show how information (...) and communication technologies enhance the reliability, scalability, and connectivity of crowdsourced e-research, giving online citizen science projects powerful epistemic advantages over more traditional modes of scientific investigation. These results highlight the essential role played by technologically mediated social interaction in contemporary knowledge production. We conclude by calling for an explicitly sociotechnical turn in the philosophy of science that combines insights from statistics and logic to analyse the latest developments in scientific research. (shrink)

Discovering high-level causal relations from low-level data is an important and challenging problem that comes up frequently in the natural and social sciences. In a series of papers, Chalupka etal. (2015, 2016a, 2016b, 2017) develop a procedure forcausal feature learning (CFL) in an effortto automate this task. We argue that CFL does not recommend coarsening in cases where pragmatic considerations rule in favor of it, and recommends coarsening in cases where pragmatic considerations rule against it. We propose a new technique, (...) pragmatic causal feature learning (PCFL), which extends the original CFL algorithm in useful and intuitive ways. We show that PCFL has the same attractive measure-theoretic properties as the original CFL algorithm. We compare the performance of both methods through theoretical analysis and experiments. (shrink)

Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence (XAI), a fast-growing research area that is so far lacking in firm theoretical foundations. Building on work in logic, probability, and causality, we establish the central role of necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We provide a sound and complete algorithm for computing explanatory factors (...) with respect to a given context, and demonstrate its flexibility and competitive performance against state of the art alternatives on various tasks. (shrink)

The modern abundance and prominence of data has led to the development of “data science” as a new field of enquiry, along with a body of epistemological reflections upon its foundations, methods, and consequences. This article provides a systematic analysis and critical review of significant open problems and debates in the epistemology of data science. We propose a partition of the epistemology of data science into the following five domains: (i) the constitution of data science; (ii) the kind of enquiry (...) that it identifies; (iii) the kinds of knowledge that data science generates; (iv) the nature and epistemological significance of “black box” problems; and (v) the relationship between data science and the philosophy of science more generally. (shrink)

ABSTRACT In order to explore what it means to pursue philosophical investigations for theological reasons, this paper argues that Ludwig Wittgenstein continues and corrects Pseudo-Denys’ project in The Divine Names. I first argue that The Divine Names should be interpreted as attempting to render human thought transparent to the divine by relativizing our concepts. The success of this project is compromised because the concept of ‘unity’ is not relativized. I then develop the claim that Wittgenstein does relativize unity in a (...) similar way and for similar religious reasons to Pseudo-Denys. As such, he can be read as continuing and correcting the Pseudo-Dionysian project. I conclude by reflecting on several of this argument’s implications for the relationship between philosophy and Christian systematic theology. (shrink)

Hortense Spillers asserts the imperative for black writers to reconfigure the languages they inherit. One way of doing so is to craft counter-myths against dominative mythologies. Spillers casts myth as an integration of form and concept which overdetermines the significance of what it is used to talk about. One crucial effect of America’s racialising mythos has been to deny black women the ability to determine that significance. She then describes how this mythos is crafted through a double wounding that creates (...) at least two ‘interstices’—first between home and market, then between blackness and humanity—which are covered up by mythological terms. Finally, Spillers shows how counter-mythologies can be crafted by speaking from within these interstices to reconfigure the conditions of possibility governing meaningful speech, taking the 19th- century African-American preaching tradition as her example. The article concludes by reflecting on what it might mean to practice Christian theology as counter-mythology in light of Spillers’ work through a reading of Edwidge Danticat’s The Dew Breaker. (shrink)

I explore the political, economic, and cultural consequences of globalization of the reduction of space in the world. This work compares and contrasts the philosophical implications Jameson (and Marx) and Sloterdijk (with Heidegger) of globalization. The film 2001: A Space Odyssey is discussed as a metaphor for the cultural narratives Jameson and Sloterdijk provide.

I briefly compare and contrast the philosophy of Confucius as written in the I Ching and Lao Tzu's philosophy presented in the Tao Te Ching.

I briefly discuss the issues with Aristotle's concept of balance and justice and contrast this with the concept of liberty argued by Camus.

I briefly discuss the philosophical reasons for preferring the future over the present.

I briefly discuss the problems of Chisholm's entia successiva--the mind and body being successive parts of a machine.

I briefly discuss and support the concept of social utility proposed by Hume.

http://www.slimmerbetteryou.com Talks about weight loss principles and facts that need to be understood perfectly well.