Generative deep learning has sparked a new wave of Super-Resolution (SR) algorithms that enhance single images with impressive aesthetic results, albeit with imaginary details. Multi-frame Super-Resolution (MFSR) offers a more grounded approach to the ill-posed problem, by conditioning on multiple low-resolution views. This is important for satellite monitoring of human impact on the planet -- from deforestation, to human rights violations -- that depend on reliable imagery. To this end, we present HighRes-net, the first deep learning approach to MFSR that learns its sub-tasks in an end-to-end fashion: (i) co-registration, (ii) fusion, (iii) up-sampling, and (iv) registration-at-the-loss. Co-registration of low-resolution views is learned implicitly through a reference-frame channel, with no explicit registration mechanism. We learn a global fusion operator that is applied recursively on an arbitrary number of low-resolution pairs. We introduce a registered loss, by learning to align the SR output to a ground-truth through ShiftNet. We show that by learning deep representations of multiple views, we can super-resolve low-resolution signals and enhance Earth Observation data at scale. Our approach recently topped the European Space Agency's MFSR competition on real-world satellite imagery.

A new methodology is developed for joint analysis of a matrix and accompanying documents, with the documents associated with the matrix rows/columns. The documents are modeled with a focused topic model, inferring latent binary features (topics) for each document. A new matrix decomposition is developed, with latent binary features associated with the rows/columns, and with imposition of a low-rank constraint. The matrix decomposition and topic model are coupled by sharing the latent binary feature vectors associated with each. The model is applied to roll-call data, with the associated documents defined by the legislation.

Barry O'Sullivan from the Insight Research Centre for Data Analytics writes about the EU's plans for regulating AI – and what opportunities it could hold for Ireland. The new president of the European Commission, Ursula von der Leyen, committed to introducing a new European regulation for artificial intelligence (AI) in Europe during her first 100 days in office. While a fully fledged regulation is unlikely in that timeframe, we can expect to see a vision for a new regulatory framework for AI in Europe very soon, possibly this month. What can we expect from such a regulation and what should AI developers and businesses be doing to prepare for it? The EU is positioning itself as a leader in trustworthy, human-centric artificial intelligence.

Inspired by "predictive coding" - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural networks, PCN includes both feedback connections, which carry top-down predictions, and feedforward connections, which carry bottom-up errors of prediction. Feedback and feedforward connections enable adjacent layers to interact locally and recurrently to refine representations towards minimization of layer-wise prediction errors. When unfolded over time, the recurrent processing gives rise to an increasingly deeper hierarchy of non-linear transformation, allowing a shallow network to dynamically extend itself into an arbitrarily deep network. Despite notably fewer layers and parameters, PCN achieves competitive performance compared to classical and state-of-the-art models.

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group.

The Equalized Odds (for short, EO) is one of the most popular measures of discrimination used in the supervised learning setting. It ascertains fairness through the balance of the misclassification rates (false positive and negative) across the protected groups -- e.g., in the context of law enforcement, an African-American defendant who would not commit a future crime will have an equal opportunity of being released, compared to a non-recidivating Caucasian defendant. Despite this noble goal, it has been acknowledged in the literature that statistical tests based on the EO are oblivious to the underlying causal mechanisms that generated the disparity in the first place (Hardt et al. 2016). This leads to a critical disconnect between statistical measures readable from the data and the meaning of discrimination in the legal system, where compelling evidence that the observed disparity is tied to a specific causal process deemed unfair by society is required to characterize discrimination. The goal of this paper is to develop a principled approach to connect the statistical disparities characterized by the EO and the underlying, elusive, and frequently unobserved, causal mechanisms that generated such inequality.

We have all heard about the increase in facial recognition and artificial intelligence. Whether this sparks scenes from the movie "Smart House" or gets your gears grinding for new possibilities, I think we can all agree that it feels a little outlandish how far this technology has come. What we do not necessarily realize is the extent to which this technology is already being used in unstable, crucial areas -- primarily, criminal justice. Criminal justice is a topic that many find to be easily understandable, and therefore easily marketable. Though not all Americans fully understand tax code, almost all if not all, have a general understanding of what it means when a paper has a headline, "Crime Spikes in College Town."

Clearview AI is "Orwellian," a new lawsuit alleges. Clearview AI, a controversial facial recognition app being used by US law enforcement to identify suspects and other people, is facing another lawsuit. The new suit, filed Thursday, seeks class-action status and $5 million in damages for what it calls willful, reckless or negligent violations of biometrics laws in Illinois by Clearview and CDW. It's fighting Clearview's collection, storage and use of biometric information without written consent, which is illegal, according to the lawsuit, which was spotted earlier Thursday by BuzzFeed. The app identifies people by comparing photos to a database of images scraped from social media and other sites. It came under fire after a New York Times investigation into the software company last month, with Clearview AI being called a "chilling" privacy risk by Democratic Sen. Edward Markey in late January.

Law enforcement agencies around the world are enthusiastically adopting the services of Clearview AI, a tech company whose powerful software scrapes several billion open-source images for the purposes of facial recognition. As the company confronts mounting criticism over its disturbing surveillance practices, its CEO, Hoan Ton-That, is rolling out an audacious new defense: he claims that Clearview's practices are protected by the first amendment. Ton-That's upside-down views of civil liberties are, it seems, just as Orwellian as his company's surveillance apparatus. Fortunately he is dead wrong. The constitution does not shield Clearview AI from accountability.

Imagine a random walk that outputs a state only when visiting it for the first time. The observed output is therefore a repeat-censored version of the underlying walk, and consists of a permutation of the states or a prefix of it. We call this model initial-visit emitting random walk (INVITE). Prior work has shown that the random walks with such a repeat-censoring mechanism explain well human behavior in memory search tasks, which is of great interest in both the study of human cognition and various clinical applications. However, parameter estimation in INVITE is challenging, because naive likelihood computation by marginalizing over infinitely many hidden random walk trajectories is intractable. In this paper, we propose the first efficient maximum likelihood estimate (MLE) for INVITE by decomposing the censored output into a series of absorbing random walks.