We are in the foothills of an AI journey. On April 8 the EU issued in-depth guidelines on developing and implementing trustworthy Artificial Intelligence. The guidelines identify fundamental requirements for AI in Europe and set a global standard for efforts to advance AI that is Ethical and Responsible. "It's like putting the foundations in before you build a house. Now is the time to do it," said Liam Benham, Vice President, Government and Regulatory Affairs, in Europe.

About Singularity University: Singularity University is a benefit corporation headquartered at NASA's research campus in Silicon Valley. We provide educational programs, innovative partnerships and a startup accelerator to help individuals, businesses, institutions, investors, NGOs and governments understand cutting-edge technologies, and how to utilize these technologies to positively impact billions of people.

Climate change: I am inevitable. Robert Downey Jr.: I am Iron Man. That's basically what went down during the opening keynote at Amazon's new re:MARS tech and innovation conference in Las Vegas. Avengers actor Robert Downey Jr. made the very Tony Stark-like announcement that he'd be launching a new organization focused on solving environmental woes using artificial intelligence and other advanced technologies. "Between robotics and technology, we could probably clean up the planet significantly, if not entirely, within a decade," he said on Tuesday night.

Artificial intelligence is putting new teeth on the old saw that cheaters never prosper. New companies and new research are applying the cutting edge technology in at least three different ways to combat cheating -- on homework, on the job hunt and even on one's diet. In California, a new company called Crosschq is using machine learning and data analytics to help employers with the job reference process. The technology is meant to help companies avoid bad hires and compare how job candidates present themselves with how their references see them. In Pennsylvania, Drexel University researchers are developing an app that can predict when dieters are likely to lapse on their eating regimen, based on the time of day, the user's emotions -- even the temperature of their skin and heart rate.

There is a simple riposte to anyone who doubts an Olympics can truly transform a city: Tokyo. When Japan's capital first won the right to host the Games, in 1959, it suffered from a desperate shortage of housing and functional infrastructure – and the lack of flush toilets meant most waste had to be vacuumed daily out of cesspits underneath buildings by "honey wagon" trucks. But within five years Japan's capital had undergone such a metamorphosis that visitors to the 1964 Olympics responded with stunned awe. "Out of the jungle of concrete mixers, mud and timber that has been Tokyo for years, the city has emerged, as from a chrysalis, to stand glitteringly ready for the Olympics," the Times' correspondent swooned, citing a long list of buildings and accomplishments "all blurring into a neon haze … that will convince the new arrival he has come upon a mirage." As Japan's capital enters a year in the spotlight, from the Rugby World up to the 2020 Olympics, Guardian Cities is spending a week reporting live from the largest megacity on Earth.

The Koopman operator has emerged as a powerful tool for the analysis of nonlinear dynamical systems as it provides coordinate transformations which can globally linearize the dynamics. Recent deep learning approaches such as Linearly-Recurrent Autoencoder Networks (LRAN) show great promise for discovering the Koopman operator for a general nonlinear dynamical system from a data-driven perspective, but several challenges remain. In this work, we formalize the problem of learning the continuous-time Koopman operator with deep neural nets in a measure-theoretic framework. This induces two forms of models: differential and recurrent form, the choice of which depends on the availability of the governing equation and data. We then enforce a structural parameterization that renders the realization of the Koopman operator provably stable. A new autoencoder architecture is constructed, such that only the residual of the dynamic mode decomposition is learned. Finally, we employ mean-field variational inference (MFVI) on the aforementioned framework in a hierarchical Bayesian setting to quantify uncertainties in the characterization and prediction of the dynamics of observables. The framework is evaluated on a simple polynomial system, the Duffing oscillator, and an unstable cylinder wake flow with noisy measurements.

The backpropagation algorithm has long been the canonical training method for neural networks. Modern paradigms are implicitly optimized for it, and numerous guidelines exist to ensure its proper use. Recently, synthetic gradients methods - where the error gradient is only roughly approximated - have garnered interest. These methods not only better portray how biological brains are learning, but also open new computational possibilities, such as updating layers asynchronously. Even so, they have failed to scale past simple tasks like MNIST or CIFAR-10. This is in part due to a lack of standards, leading to ill-suited models and practices forbidding such methods from performing to the best of their abilities. In this work, we focus on direct feedback alignment and present a set of best practices justified by observations of the alignment angles. We characterize a bottleneck effect that prevents alignment in narrow layers, and hypothesize it may explain why feedback alignment methods have yet to scale to large convolutional networks.

The study focuses on estimating and predicting time-varying origin to destination (OD) trip tables for a dynamic traffic assignment (DTA) model. A bi-level optimisation problem is formulated and solved to estimate OD flows from pre-existent demand matrix and historical traffic flow counts. The estimated demand is then considered as an input for a time series OD demand prediction model to support the DTA model for short-term traffic condition forecasting. Results show a high capability of the proposed OD demand estimation method to reduce the DTA model error through an iterative solution algorithm. Moreover, the applicability of the OD demand prediction approach is investigated for an incident analysis application for a major corridor in Sydney, Australia.

While physicalism requires only that a conscious state depends entirely on an underlying physical state, it is often assumed that consciousness is algorithmic and that conscious states can be copied, such as by copying or digitizing the human brain. In an effort to further elucidate the physical nature of consciousness, I challenge these assumptions and attempt to prove the Single Stream of Consciousness Theorem ("SSCT"): that a conscious entity cannot experience more than one stream of consciousness from a given conscious state. Assuming only that consciousness is a purely physical phenomenon, it is shown that both Special Relativity and Multiverse theory independently imply SSCT and that the Many Worlds Interpretation of quantum mechanics is inadequate to counter it. Then, SSCT is shown to be incompatible with Strong Artificial Intelligence, implying that consciousness cannot be created or simulated by a computer. Finally, SSCT is shown to imply that a conscious state cannot be physically reset to an earlier conscious state nor can it be duplicated by any physical means. The profound but counterintuitive implications of these conclusions are briefly discussed.

This paper presents a novel approach to numerically solve stochastic differential games for nonlinear systems. The proposed approach relies on the nonlinear Feynman-Kac theorem that establishes a connection between parabolic deterministic partial differential equations and forward-backward stochastic differential equations. Using this theorem the Hamilton-Jacobi-Isaacs partial differential equation associated with differential games is represented by a system of forward-backward stochastic differential equations. Numerical solution of the aforementioned system of stochastic differential equations is performed using importance sampling and a Long-Short Term Memory recurrent neural network, which is trained in an offline fashion. The resulting algorithm is tested on two example systems in simulation and compared against the standard risk neutral stochastic optimal control formulations.