In complex areas such as law and science, knowledge has been in centuries formulated by primarily describing prototypical instances and properties, and then by overriding the general theory to include possible exceptions. For example, many laws are formulated by adding new norms that, in case of conflicts, may partially or completely override the previous ones. Similarly, biologists have been incrementally introducing exceptions to general properties. For instance, the human heart is usually located in the left-hand half of the thorax. Still there are exceptional individuals, with so-called situs inversus, whose heart is located on the opposite side. Eukariotic cells are those with a proper nucleus, by definition. Still they comprise mammalian red blood cells, that in their mature stage have no nucleus.

Data-driven predictive models are increasingly used in education to support students, instructors, and administrators. However, there are concerns about the fairness of the predictions and uses of these algorithmic systems. In this introduction to algorithmic fairness in education, we draw parallels to prior literature on educational access, bias, and discrimination, and we examine core components of algorithmic systems (measurement, model learning, and action) to identify sources of bias and discrimination in the process of developing and deploying these systems. Statistical, similarity-based, and causal notions of fairness are reviewed and contrasted in the way they apply in educational contexts. Recommendations for policy makers and developers of educational technology offer guidance for how to promote algorithmic fairness in education.

When analysing a complex system, very often an answer to one question raises new questions. This also applies to the explanatory analysis of machine learning models. We cannot sufficiently explain a complex model using a single method that gives only one perspective. Isolated explanations are prone to misunderstanding, which inevitably leads to wrong reasoning. Surprisingly, the majority of methods developed for Explainable Artificial Intelligence (XAI) focus on a single aspect of the model behaviour. In this paper, we show the problem of model explainability as an interactive and sequential analysis of a model. We show how different XAI methods complement each other and why it is essential to juxtapose them together. The proposed process of Interactive Explanatory Model Analysis (IEMA) derives from the theoretical, algorithmic side of the model explanation and aims to embrace ideas developed in cognitive sciences. Its grammar is implemented in the modelStudio framework that adopts interactivity, customisability and automation as its main traits.

The following questions are fundamental to understanding the properties of over-parameterization in modern machine learning: (1) Under what conditions and at what rate does training converge to a global minimum? (2) What form of implicit regularization occurs through training? While significant progress has been made in answering both of these questions for gradient descent, they have yet to be answered more completely for general optimization methods. In this work, we establish sufficient conditions for linear convergence and obtain approximate implicit regularization results for generalized mirror descent (GMD), a generalization of mirror descent with a possibly time-dependent mirror. GMD subsumes popular first order optimization methods including gradient descent, mirror descent, and preconditioned gradient descent methods such as Adagrad. By using the Polyak-Lojasiewicz inequality, we first present a simple analysis under which non-stochastic GMD converges linearly to a global minimum. We then present a novel, Taylor-series based analysis to establish sufficient conditions for linear convergence of stochastic GMD. As a corollary, our result establishes sufficient conditions and provides learning rates for linear convergence of stochastic mirror descent and Adagrad. Lastly, we obtain approximate implicit regularization results for GMD by proving that GMD converges to an interpolating solution that is approximately the closest interpolating solution to the initialization in l2-norm in the dual space, thereby generalizing the result of Azizan, Lale, and Hassibi (2019) in the full batch setting.

In this paper, we consider data acquired by multimodal sensors capturing complementary aspects and features of a measured phenomenon. We focus on a scenario in which the measurements share mutual sources of variability but might also be contaminated by other measurement-specific sources such as interferences or noise. Our approach combines manifold learning, which is a class of nonlinear data-driven dimension reduction methods, with the well-known Riemannian geometry of symmetric and positive-definite (SPD) matrices. Manifold learning typically includes the spectral analysis of a kernel built from the measurements. Here, we take a different approach, utilizing the Riemannian geometry of the kernels. In particular, we study the way the spectrum of the kernels changes along geodesic paths on the manifold of SPD matrices. We show that this change enables us, in a purely unsupervised manner, to derive a compact, yet informative, description of the relations between the measurements, in terms of their underlying components. Based on this result, we present new algorithms for extracting the common latent components and for identifying common and measurement-specific components.

The majority of adversarial machine learning research focuses on additive threat models, which add adversarial perturbation to input data. On the other hand, unlike image recognition problems, only a handful of threat models have been explored in the video domain. In this paper, we propose a novel adversarial attack against video recognition models, Multiplicative Adversarial Videos (MultAV), which imposes perturbation on video data by multiplication. MultAV has different noise distributions to the additive counterparts and thus challenges the defense methods tailored to resisting additive attacks. Moreover, it can be generalized to not only Lp-norm attacks with a new adversary constraint called ratio bound, but also different types of physically realizable attacks. Experimental results show that the model adversarially trained against additive attack is less robust to MultAV.

Amid the cacophony of concern over artificial intelligence (AI) taking over jobs (and the world) and cheers for what it can do to increase productivity and profits, the potential for AI to do good can be overlooked. Technology leaders such as Microsoft, IBM, Huawei and Google have entire sections of their business focused on the topic and dedicate resources to build AI solutions for good and to support developers who do. In the fight to solve extraordinarily difficult challenges, humans can use all the help we can get. Here are 8 powerful examples of artificial intelligence for good as it is applied to some of the toughest challenges facing society today. There are more than 1 billion people living with a disability around the world.

For years, a group of Chinese hackers known variously as Barium, Winnti, or APT41 has carried out a unique mix of sophisticated hacking activities that has puzzled the cybersecurity researchers tracking them. At times they appear focused on the usual state-sponsored espionage, believed to be working in the service of the Chinese Ministry of State Security. At other times their attacks looked more like traditional cybercrime. Now a set of federal indictments has called out those intruders by name, and cast their activities in a new light. Five Chinese hackers are accused of a sprawling scheme to break into the networks of hundreds of global companies in a broad range of industries, as well as think tanks, universities, foreign government agencies, and the accounts of Hong Kong government officials and pro-democracy activists.

While investors were holding onto their seats, anxiously awaiting the Feds final announcement before November elections, markets were green and extending the gains of the past two days. The Dow was up 100 points higher (0.4%), and the S&P 500 up 0.3%. The Nasdaq, however, showed some signs of cooling off from its strong recovery after last week's rout, only gaining 0.1%. The Fed's announcement today should surely move the markets more. Investors are anticipating Chairman Jay Powell's announcement that the Fed will keep rates at or near 0% through 2023, an unprecedented policy shift and stimulus to the economy.

What do they all have in common? If you've been paying attention to cybersecurity news this past year, then you already know. All of them have experienced truly staggering data breaches in 2020. Hackers have learned to deploy every technology and trick up their sleeves to steal data, cause disruption, and exploit the billions of people out there just trying to use the internet. Fortunately, the last few years have seen the rise of new technologies that finally give us an effective way of fighting back against hackers.