The Intuitive Appeal of Explainable Machines

Abstract

As algorithmic decision-making has become synonymous with inexplicable decision-making, we have become obsessed with opening the black box. This Article responds to a growing chorus of legal scholars and policymakers demanding explainable machines. Their instinct makes sense; what is unexplainable is usually unaccountable. But the calls for explanation are a reaction to two distinct but often conflated properties of machine-learning models: inscrutability and non intuitiveness. Inscrutability makes one unable to fully grasp the model, while non intuitiveness means one cannot understand why the model’s rules are what they are. Solving inscrutability alone will not resolve law and policy concerns; accountability relates not merely to how models work, but whether they are justified.

In this Article, we first explain what makes models inscrutable as a technical matter. We then explore two important examples of existing regulation-by-explanation and techniques within machine learning for explaining inscrutable decisions. We show that while these techniques might allow machine learning to comply with existing laws, compliance will rarely be enough to assess whether decision-making rests on a justifiable basis.

We argue that calls for explainable machines have failed to recognize the connection between intuition and evaluation and the limitations of such an approach. A belief in the value of explanation for justification assumes that if only a model is explained, problems will reveal themselves intuitively. Machine learning, however, can uncover relationships that are both non-intuitive and legitimate, frustrating this mode of normative assessment. If justification requires understanding why the model’s rules are what they are, we should seek explanations of the process behind a model’s development and use, not just explanations of the model itself. This Article illuminates the explanation-intuition dynamic and offers documentation as an alternative approach to evaluating machine learning models.

Full abstract and research here:

http://blog.experientia.com/paper-intuitive-appeal-explainable-machines/

Connotation Frames of Power and Agency in Modern Films

The framing of an action influences how we perceive its actor. We introduce connotation frames of power and agency, a pragmatic formalism organized using frame semantic representations, to model how different levels of power and agency are implicitly projected on actors through their actions. We use the new power and agency frames to measure the subtle, but prevalent, gender bias in the portrayal of modern film characters and provide insights that deviate from the well-known Bechdel test. Our contributions include an extended lexicon of connotation frames along with a web interface that provides a comprehensive analysis through the lens of connotation frames.

ETHICALLY ALIGNED DESIGN A Vision for Prioritizing Human Well-being with Autonomous and Intelligent Systems - IEEE

Introduction As the use and impact of autonomous and intelligent systems (A/IS) become pervasive, we need to establish societal and policy guidelines in order for such systems to remain human-centric, serving humanity’s values and ethical principles. These systems have to behave in a way that is beneficial to people beyond reaching functional goals and addressing technical problems. This will allow for an elevated level of trust between people and technology that is needed for its fruitful, pervasive use in our daily lives. To be able to contribute in a positive, non-dogmatic way, we, the techno-scientific communities, need to enhance our self-reflection, we need to have an open and honest debate around our imaginary, our sets of explicit or implicit values, our institutions, symbols and representations. Eudaimonia, as elucidated by Aristotle, is a practice that defines human well-being as the highest virtue for a society. Translated roughly as “flourishing,” the benefits of eudaimonia begin by conscious contemplation, where ethical considerations help us define how we wish to live. Whether our ethical practices are Western (Aristotelian, Kantian), Eastern (Shinto, Confucian), African (Ubuntu), or from a different tradition, by creating autonomous and intelligent systems that explicitly honor inalienable human rights and the beneficial values of their users, we can prioritize the increase of human well-being as our metric for progress in the algorithmic age. Measuring and honoring the potential of holistic economic prosperity should become more important than pursuing one-dimensional goals like productivity increase or GDP growth.

AI, Algorithms, Accountability of AI, Bias, Explanation, Machine Learning, ResearchBrigitte BellanDecember 17, 2017IEEE, Ethics, Well-Being, Design

Unconscious bias - The Royal Society

Adapted by Professor Uta Frith DBE FBA FMedSci FRS from guidance issued to recruitment panels by the Scottish Government

Introduction

All panels and committees for selection and appointments at The Royal Society should be carried out objectively and professionally.

The Society is committed to making funding or award decisions purely on the basis of the quality of the proposed science and merit of the individual. No funding applicant or nominee for awards, Fellowship, Foreign Membership, election to a post or appointment to a committee should receive less favourable treatment on the grounds of: gender, marital status, sexual orientation, gender re-assignment, race, colour, nationality, ethnicity or national origins, religion or similar philosophical belief, spent criminal conviction, age or disability.

Research, BiasBrigitte BellanNovember 26, 2017The Royal Society

GENDER BIAS IN ADVERTISING

In 2017, discussions around gender and media have reached a fever pitch. Following a bruising year at the ballot box, fourth-wave feminism has continued to expand. From the Women’s March to high-profile sexual harassment trials to the increasing number of female protagonists gaining audience recognition in an age of “peak TV,” women are ensuring that their concerns are heard and represented.

We’ve seen movements for gender equality in Hollywood, in Silicon Valley — and even on Madison Avenue. In response to longstanding sexism in advertising, industry leaders such as Madonna Badger are highlighting how objectification of women in advertising can lead to unconscious biases that harm women, girls and society as a whole.

Agencies are creating marquee campaigns to support women and girls. The Always #LikeAGirl campaign, which debuted in 2014, ignited a wave of me-too “femvertising” campaigns: #GirlsCan from Cover Girl, “This Girl Can” from Sport England and the UK’s National Lottery, and a spot from H&M that showcased women in all their diversity, set to “She’s a Lady.” Cannes Lions got in on the act in 2015, introducing the Glass Lion: The Lion for Change, an award to honor ad campaigns that address gender inequality or prejudice.

But beyond the marquee case studies, is the advertising industry making strides toward improving representation of women overall? How do we square the surge in “femvertising” with insights from J. Walter Thompson’s Female Tribes initiative, which found in 2016 that, according to 85% of women, the advertising world needs to catch up with the real world?

Evidence That Gendered Wording in Job Advertisements Exists and Sustains Gender Inequality

Women continue to remain underrepresented in male-dominated fields such as engineering, the natural sciences, and business. Research has identified a range of individual factors such as beliefs and stereotypes that affect these disparities but less is documented around institutional factors that perpetuate gender inequalities within the social structure itself (e.g., public policy or law). These institutional factors can also influence people’s perceptions and attitudes towards women in these fields, as well as other individual factors.

Algorithmic Accountability Reporting: On the Investigation of Black Boxes

How can we characterize the power that various algorithms may exert on us? And how can we better understand when algorithms might be wronging us? What should be the role of journalists in holding that power to account? In this report I discuss what algorithms are and how they encode power. I then describe the idea of algorithmic accountability, first examining how algorithms problematize and sometimes stand in tension with transparency.

GloVe: Global Vectors for Word Representation

Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic , but the origin of these regularities has remained opaque. We analyze and make explicit the model properties needed for such regularities to emerge in word vectors. The result is a new global log-bilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods. Our model efficiently leverages statistical information by training only on the nonzero elements in a word-word co-occurrence matrix, rather than on the entire sparse matrix or on individual context windows in a large corpus. The model produces a vector space with meaningful sub-structure, as evidenced by its performance of 75% on a recent word analogy task. It also outperforms related models on similarity tasks and named entity recognition.

AI, Research, Gender Bias, NLPBrigitte BellanJuly 2, 2017GloVe, Stanford University, Word Vector

Penn Psychologists Tap Big Data, Twitter to Analyze Accuracy of Stereotypes

What’s in a tweet? People draw conclusions about us, from our gender to education level, based on the words we use on social media. Researchers from the University of Pennsylvania, along with colleagues from the Technical University of Darmstadt and the University of Melbourne, have now analyzed the accuracy of those inferences. Their work revealed that, though stereotypes and the truth often aligned, with people making accurate assumptions more than two-thirds of the time, inaccurate characterizations still showed up.