Deep neural networks (DNNs) have found their way into many applications with potential impact on the safety, security, and fairness of human-machine-systems. Such require basic understanding and sufficient trust by the users. This motivated the research field of explainable artificial intelligence (XAI), i.e. finding methods for opening the "black-boxes" DNNs represent. For the computer vision domain in specific, practical assessment of DNNs requires a globally valid association of human interpretable concepts with internals of the model. The research field of concept (embedding) analysis (CA) tackles this problem: CA aims to find global, assessable associations of humanly interpretable semantic concepts (e.g., eye, bearded) with internal representations of a DNN. This work establishes a general definition of CA and a taxonomy for CA methods, uniting several ideas from literature. That allows to easily position and compare CA approaches. Guided by the defined notions, the current state-of-the-art research regarding CA methods and interesting applications are reviewed. More than thirty relevant methods are discussed, compared, and categorized. Finally, for practitioners, a survey of fifteen datasets is provided that have been used for supervised concept analysis. Open challenges and research directions are pointed out at the end.

The U.S. refrained from designating any trading partner as a currency manipulator in the Biden administration's first foreign-exchange policy report, even as Switzerland, Taiwan and Vietnam met thresholds for the label.The Treasury Department said Friday that those three economies met criteria for the manipulator label, including a large trade surplus with the U.S. In December, the last report done under President Donald Trump designated Switzerland and Vietnam as manipulators.The new assessments signal the Biden administration is taking a less confrontational approach to international currency policy after Trump labeling of China and other countries as manipulators proved ineffective and spurred concerns of politicization.The latest report assesses currency activities through 2020.Covid ImpactThe U.S. acknowledged that the unprecedented nature of the coronavirus pandemic's impact on the global economy led to creative policy responses by governments and central banks.

In Christopher Nolan's film Tenet, the future is at war with the past "because the oceans rose and the rivers ran dry." Thanks to catastrophic climate change, no path lay ahead for our descendants, and their only hope was to carve out a future by orchestrating a genocide in our past. As the film's protagonist, Neil, explains: "Every generation looks out for its own survival." It's hard to watch a film like Tenet and not contemplate the longer-term consequences of our actions -- how will the future judge us? Working in product, we tend to approach most opportunities with good intention.

Ukraine is using facial recognition software to help identify the bodies of Russian soldiers killed in combat and track down their families to inform them of their deaths, Ukraine's vice-prime minister told the Reuters news service. Mykhailo Fedorov, Ukraine's vice-prime minister who also runs the ministry of digital transformation, told Reuters his country had been using software facial recognition provider Clearview AI to find the social media accounts of dead Russian soldiers. "As a courtesy to the mothers of those soldiers, we are disseminating this information over social media to at least let families know that they they've lost their sons and to then enable them to come to collect their bodies," Fedorov said in an interview, speaking via a translator. Ukraine's Ministry of Defense this month began using technology from Clearview, which scrapes images on the web to match with faces featured in uploaded photos. Reuters first reported Ukraine's use of Clearview earlier this month, but it was not clear at that time how the technology would be used.

Your browser does not support the video element. The hero of the Halo video game franchise, Master Chief, made his debut in 2001 in the game "Halo: Combat Evolved" for the original Xbox game console. In the time since, he has become Microsoft's version of Mario, though just a bit grittier. The Chief, in his iconic green armor, and his fellow superhuman Spartans are more juggernauts than soldiers. Weighing a half-ton, and able to absorb anything short of a tank shell, the armor includes technological enhancements that improve everything from vision to reflexes, turning Spartans into the ultimate weapons.

Clearview AI claims to be the world's "largest facial network," drawing from a database of more than 10 billion images scraped from publicly-available websites, including social media profiles, for use by customers including law enforcement agencies. Ukrainian authorities are messaging relatives to suggest they come and collect the bodies, Federov told Reuters, adding that the percentage of soldiers the software had recognised claimed by families had been "high." The true number of Russian soldiers to have died in Ukraine is unknown. While the Russian defense ministry admitted 498 of its troops had been killed in early March, US and Ukrainian officials estimate the total number of deaths is significantly higher. Yesterday NATO released estimates that up to 40,000 Russian troops have been killed, wounded, taken prisoner, or gone missing.

Banks and other financial institutions utilizing artificial intelligence may be uniquely susceptible to retaliatory Russian cyberattacks as taxing international sanctions worsen, experts warn. Those fears, highlighted in a recent Wall Street Journal report, comes as Russia's war on Ukraine trundles forward into its second month and as an unprecedented barrage of international sanctions continue to chip away at the Russian economy. Andrew Burt, a former policy adviser to the head of the cyber division at the FBI, described AI vulnerabilities as "significant and very widely overlooked" at many financial institutions that have come to rely on them. "I haven't seen any real abilities in terms of being able to defend against the flood of disinformation," Montreal AI Ethics Institute Founder Abhishek Gupta told The Journal. While those security weaknesses are cause for concern even in the best of times, government leaders including President Biden worry Russia may use cyberattacks to lash out against these institutions as sanctions take a continued toll.

Hosted by the Alan Turing Institute, AI UK is a two day conference that showcases artificial intelligence and data science research, development, and policy in the UK. This year, the event took place on 22 and 23 March, and participants were treated to a variety of interesting talks, panel discussions, and conversations on a wide variety of topics. The past year has seen much activity in the UK with regards to strategy, governance and policy. The policy-related sessions at AI UK provided the opportunity for participants to find out more about, amongst other things, the progress of AI-related legislation, regulation, the national AI strategy, the national AI Standards Hub, and how data is used at a governmental level. We take a look at three of the policy and strategy-related sessions that took place during the two days.

Before the devastating eruption of Mount Vesuvius in 79 AD, Pompeii was a thriving city with a population of up to 20,000 people. Now, scientists have delved deeper into one of Pompeii's most beautiful homes, the House of Greek Epigrams. While the house has been damaged through centuries of neglect, weathering and volcanic eruptions, researchers from Lund University have been able to rebuild it, using virtual reality and eye-tracking technology. 'Eye-tracking technology and virtual reality do now provide unprecedented opportunities to assess the visual qualities of ancient spaces,' said Dr Giacomo Landeschi, co-author of the study. Moment Miley Cyrus' plane was struck by lightning The House of Greek Epigrams is an impressive home in northeast Pompeii that was once decorated with intricate frescoes.

Did you miss a session at the Data Summit? Today, C3 AI's CEO Thomas Siebel announced the third group of Digital Transformation Institute (DTI) grant recipients to accelerate the development of artificial intelligence (AI) and machine learning (ML) technologies in hopes to combat emerging threats. As an organization, C3 AI provides enterprises with an AI Application platform they can use to create, deploy, and manage AI applications for use cases like fraud detection, network health, supply network optimization, energy management, and more. The grant was established in March 2020 by C3 AI, Microsoft, and some of the world's leading universities. The goal is to engage the world's top scientists through cash grants to encourage them to conduct research and train practitioners on AI, machine learning, Cloud computing, IoT, big data analytics, organizational behavior, public policy, and ethics.