Following a full-day livestream, we now have a better idea of when and where the next game in Ubisoft's long-running Assassin's Creed franchise will take place. In Assassin's Creed: Valhalla, you'll play an assassin at some point during the Viking Age, which took place between 793 and 1066 CE. Publisher and developer Ubisoft picked the unconventional route of announcing the new game through a Photoshop livestream. An artist slowly and painstakingly built out the image you see above while fans speculated about the setting and classic songs from the series like "Ezio's Family" played in the background. At one point in the stream, more than 50,000 people across Twitch and YouTube tuned in to watch artist Kode Abdo work his craft.

We describe our submission to the Extreme Value Analysis 2019 Data Challenge in which teams were asked to predict extremes of sea surface temperature anomaly within spatio-temporal regions of missing data. We present a computational framework which reconstructs missing data using convolutional deep neural networks. Conditioned on incomplete data, we employ autoencoder-like models as multivariate conditional distributions from which possible reconstructions of the complete dataset are sampled using imputed noise. In order to mitigate bias introduced by any one particular model, a prediction ensemble is constructed to create the final distribution of extremal values. Our method does not rely on expert knowledge in order to accurately reproduce dynamic features of a complex oceanographic system with minimal assumptions. The obtained results promise reusability and generalization to other domains.

In many settings it is important for one to be able to understand why a model made a particular prediction. In NLP this often entails extracting snippets of an input text `responsible for' corresponding model output; when such a snippet comprises tokens that indeed informed the model's prediction, it is a faithful explanation. In some settings, faithfulness may be critical to ensure transparency. Lei et al. (2016) proposed a model to produce faithful rationales for neural text classification by defining independent snippet extraction and prediction modules. However, the discrete selection over input tokens performed by this method complicates training, leading to high variance and requiring careful hyperparameter tuning. We propose a simpler variant of this approach that provides faithful explanations by construction. In our scheme, named FRESH, arbitrary feature importance scores (e.g., gradients from a trained model) are used to induce binary labels over token inputs, which an extractor can be trained to predict. An independent classifier module is then trained exclusively on snippets provided by the extractor; these snippets thus constitute faithful explanations, even if the classifier is arbitrarily complex. In both automatic and manual evaluations we find that variants of this simple framework yield predictive performance superior to `end-to-end' approaches, while being more general and easier to train. Code is available at https://github.com/successar/FRESH

During a workshop hosted at the International Conference on Learning Representations (ICLR) 2020, taking place on the web this week, panelists discussed how AI and machine learning might be -- and already has been -- applied to agricultural challenges. As several experts pointed out, countries around the world face a food supply shortfall -- an estimated 9% of the population (697 million people) are severely "food insecure," meaning they're without reliable access to affordable, nutritious food. Factors like labor shortages, the spread of pests and pathogens, and climate change threaten to escalate the crisis. IBM scientists spoke about their work in Africa with agricultural "digital twins," or digital models of crops used to forecast specific crop yields. And a team from the University of California, Davis detailed an effort to use satellite images to predict foraging conditions for livestock in Kenya.

The coronavirus pandemic has taken a severe toll on industries, health systems and lives since the outbreak began with doctors, scientists and ordinary people racing to find ways to tackle the contagion. From robots to a virus-killing snood and a portable isolation capsule, these new prototypes demonstrate what humans are capable of in the face of adversity. Here are some of the innovations developed to combat the current outbreak that has killed more than 217,000 people and infected 3.1 million. COVID-19 attacks people's lungs making it hard for them to deliver oxygen to the blood. Ventilators, which feed oxygen into the lungs, are a crucial tool to keep people with the virus alive.

In the absence of trade shows and other physical preview events, publishers are getting creative with their video game marketing. Today, Ubisoft casually launched a livestream that will reveal the setting of the next Assassin's Creed game. But here's the wild part: instead of a simple countdown, Ubisoft is broadcasting an artist working in Adobe Photoshop. At the time of writing, the canvas shows a mysterious silhouette of a powerful figure (the next game's protagonist, presumably) in front of a split background that contains icy waters and luscious fields. Will it end with some kind of trailer, or a finished poster?

In modern mathematics, many of the biggest advances are great elaborations of theory. Mathematicians move mountains, but their strength comes from tools, highly sophisticated abstractions that can act like a robotic glove, enhancing the wearer's strength. John Conway was a throwback, a natural problem-solver whose unassisted feats often left his colleagues stunned. Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research develop ments and trends in mathe matics and the physical and life sciences. "Every top mathematician was in awe of his strength. People said he was the only mathematician who could do things with his own bare hands," said Stephen Miller, a mathematician at Rutgers University.

This week, we talked to people trying to help stem the hurt of the Covid-19 pandemic--with mixed success. One company, Zipline, is using drones to help deliver virus testing supplies and personal protective equipment in Ghana. It has accelerated efforts to bring the approach to the US, though don't expect to see helper drones in the air before later this year. Farmers, packers, and processors want to get their produce, milk, and meat to consumers, but complex supply chains--and basic economics--are proving hard to hack. Let's get you caught up.

What if we could treat the Earth like a computer, a system with an ever-flowing set of data that can be tracked, analyzed, and potentially even predicted. That's the gist of Microsoft's latest environmental initiative, which it's dubbed a "Planetary Computer." The company foresees a world where we can track just about anything happening in the world -- a forest fire in California, the river tides in Uganda -- and have all of that data readily accessible on a single AI-driven platform. If Microsoft succeeds it could reshape our relationship with the Earth entirely. Lucas Joppa, Microsoft's first chief environmental officer, boiled down the concept succinctly in an interview for the Engadget Podcast: "It's a platform that is intended to accelerate our ability to monitor, model and then ultimately manage Earth's natural systems to ask questions like, 'Where are the world's forests? Where are the world's wetlands? How fast are they changing?' And hopefully, what are the sorts of benefits that we are gaining from those ecosystems? What are the services that those ecosystems provision to people?"

A physician-turned-entrepreneur raised in Kashmir is now part of a team using big data and machine learning to help detect useful patterns in the tsunami of public health data generated world-wide by the COVID-19 crisis and do what he can for those back home. Junaid Nabi, a public health researcher at Brigham and Women's Hospital and Harvard Medical School in Boston, says his experiences with the health system in the developing world drives his current work. "Growing up in Kashmir, a society marred with social, economic, and healthcare disparities, I was exposed to the inherent inequities in my community at an early age," he said, "During the final years of my training, I had an opportunity to work with some non-profit organizations, especially the rescue teams during the Savar building collapse in Dhaka, Bangladesh." "This is when I noticed that clinical medicine does not answer all the questions clinical work asks." Nabi, who is also an Aspen New Voices Fellow, is now working with colleagues at Harvard Medical School and Harvard School of Public Health to develop digital tools that harness big data and machine learning to rapidly evaluate patterns in the data pouring in from clinical research. "I believe machine learning has an important role in COVID-19," he said.