A Dutch court has demanded that an algorithm-based system used by the government to identify and track down potential housing and benefit cheats is dropped with immediate effect. As reported by DutchNews, on Wednesday, the District Court of The Hague ruled that the system conflicts with EU human rights and privacy protections. Dubbed System Risk Indication (SyRI), the automatic, machine-learning (ML) tool was used by local Dutch authorities to draw up profiles and lists of individuals suspected of being at high risk of conducting benefits fraud. According to the publication, SyRI creates risk profiles from individuals that committed social security fraud in the past and then scans for "similar" citizen profiles, creating leads for potential investigations into others that may also be committing fraud, or be of a high risk of doing so in the future. SyRI's pooling of citizen data, otherwise kept in separate silos, gave authorities wide-ranging powers and "has been exclusively targeted at neighborhoods with mostly low-income and minority residents," according to UN human rights and poverty rapporteur Philip Alston.

Many science and engineering applications require finding solutions to planning and optimization problems by satisfying a set of constraints. These constraint problems (CPs) are typically NP-complete and can be formalized as constraint satisfaction problems (CSPs) or constraint optimization problems (COPs). Evolutionary algorithms (EAs) are good solvers for optimization problems ubiquitous in various problem domains, however traditional operators for EAs are 'blind' to constraints or generally use problem dependent objective functions; as they do not exploit information from the constraints in search for solutions. A variation of EA, Intelligent constraint handling evolutionary algorithm (ICHEA), has been demonstrated to be a versatile constraints-guided EA for continuous constrained problems in our earlier works in (Sharma and Sharma, 2012) where it extracts information from constraints and exploits it in the evolutionary search to make the search more efficient. In this paper ICHEA has been demonstrated to solve benchmark exam timetabling problems, a classic COP. The presented approach demonstrates competitive results with other state-of-the-art approaches in EAs in terms of quality of solutions. ICHEA first uses its inter-marriage crossover operator to satisfy all the given constraints incrementally and then uses combination of traditional and enhanced operators to optimize the solution. Generally CPs solved by EAs are problem dependent penalty based fitness functions. We also proposed a generic preference based solution model that does not require a problem dependent fitness function, however currently it only works for mutually exclusive constraints.

Plenty of people have a pet project that they are drawn to or consider themselves particularly good at. As the leader of the data science department at Trupanion in Seattle, David Jaw's projects are actually around pets. Jaw, GeekWire's latest Geek of the Week, uses artificial intelligence and machine learning to help automate medical insurance claims for pets, streamlining the process and removing the worry about what's covered and what's not. Born and raised in a suburb near Toronto, Jaw's family moved to Albuquerque, N.M., when he was 13 years old. He stayed there through college, where he studied mechanical engineering, pursuing a childhood dream of designing airplanes and spaceships.

The IEEE Standards Association has released a report calling for engineers to consider the impact their work will have on climate change, children, and society. The Institute of Electrical and Electronics Engineers (IEEE) is one of the largest organizations for computer scientists in the world. With hundreds of thousands of members, the group undertakes initiatives to create common standards and often consults organizations like the European Commission and OECD on matters of ethics and design principles. "It is imperative to move beyond business as usual and to prioritize the well-being of our children, starting with protecting their privacy and security online. If we fail to do this, their agency, mental health, and self-actualization as humans in any culture will be reliant on forces beyond their control," reads the report titled "Measuring What Matters in the Era of Global Warming and the Age of Algorithmic Promises." The whitepaper encapsulates change already underway at the IEEE that's in line with AI ethics principles released in spring 2019 after years of work, according to John Havens, director of the IEEE Global Initiative on Ethics of Autonomous & Intelligent Systems.

Leonard Hobbs Bio: Leonard graduated from University College Cork Ireland in 1986 with a 1st class honours degree in Electrical Engineering and was awarded the title of'graduate of the year' by the college. He completed a Masters degree at the NMRC (now called Tyndall), at UCC in 1988. He has been one of Ireland's leading technologists in the ICT sector with close to 30 years of experience, mostly with Intel, spanning leading edge research to advanced manufacturing. His last role at Intel was Director of Public Affairs with responsibility for driving Intel Ireland's policy, communications, education and community agendas. Leonard is currently the Director of Research and Innovation at Trinity College Dublin where he owns the definition and implementation of the research, innovation and enterprise strategy for the University spanning research programs development, contract management, technology transfer, entrepreneurship and enterprise partnership liaison.

The coronavirus was declared a global emergency by the World Health Organization on January 30. AI is being employed extensively to track the spread of the new deadly virus, for now dubbed the 2019-novel coronavirus (2019-nCoV). Receiving fair attention as a result is BlueDot, a venture-backed startup that has built an AI platform to process billions of pieces of data, such as from world air travel, to identify outbreaks. BlueDot issued its first alert on Dec. 31, ahead of the US Centers for Disease Control and Prevention, which issued its own warning on Jan. 6, according to an account in Forbes. BlueDot was founded by Kamran Khan, an infectious disease physician and professor of Medicine and Public Health at the University of Toronto.

This paper presents a distributionally robust Q-Learning algorithm (DrQ) which leverages Wasserstein ambiguity sets to provide probabilistic out-of-sample safety guarantees during online learning. First, we follow past work by separating the constraint functions from the principal objective to create a hierarchy of machines within the constrained Markov decision process (CMDP). DrQ works within this framework by augmenting constraint costs with tightening offset variables obtained through Wasserstein distributionally robust optimization (DRO). These offset variables correspond to worst-case distributions of modeling error characterized by the TD-errors of the constraint Q-functions. This overall procedure allows us to safely approach the nominal constraint boundaries with strong probabilistic out-of-sample safety guarantees. Using a case study of safe lithium-ion battery fast charging, we demonstrate dramatic improvements in safety and performance relative to a conventional DQN.

Convolutional neural networks (CNNs) often perform well, but their stability is poorly understood. To address this problem, we consider the simple prototypical problem of signal denoising, where classical approaches such as nonlinear diffusion, wavelet-based methods and regularisation offer provable stability guarantees. To transfer such guarantees to CNNs, we interpret numerical approximations of these classical methods as a specific residual network (ResNet) architecture. This leads to a dictionary which allows to translate diffusivities, shrinkage functions, and regularisers into activation functions, and enables a direct communication between the four research communities. On the CNN side, it does not only inspire new families of nonmonotone activation functions, but also introduces intrinsically stable architectures for an arbitrary number of layers.

We present the preliminary high-level design and features of DynamicPPL.jl, a modular library providing a lightning-fast infrastructure for probabilistic programming. Besides a computational performance that is often close to or better than Stan, DynamicPPL provides an intuitive DSL that allows the rapid development of complex dynamic probabilistic programs. Being entirely written in Julia, a high-level dynamic programming language for numerical computing, DynamicPPL inherits a rich set of features available through the Julia ecosystem. Since DynamicPPL is a modular, stand-alone library, any probabilistic programming system written in Julia, such as Turing.jl, can use DynamicPPL to specify models and trace their model parameters. The main features of DynamicPPL are: 1) a meta-programming based DSL for specifying dynamic models using an intuitive tilde-based notation; 2) a tracing data-structure for tracking RVs in dynamic probabilistic models; 3) a rich contextual dispatch system allowing tailored behaviour during model execution; and 4) a user-friendly syntax for probabilistic queries. Finally, we show in a variety of experiments that DynamicPPL, in combination with Turing.jl, achieves computational performance that is often close to or better than Stan.

Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks. However, many existing MBRL methods rely on combining greedy policies with exploration heuristics, and even those which utilize principled exploration bonuses construct dual objectives in an ad hoc fashion. In this paper we introduce Ready Policy One (RP1), a framework that views MBRL as an active learning problem, where we aim to improve the world model in the fewest samples possible. RP1 achieves this by utilizing a hybrid objective function, which crucially adapts during optimization, allowing the algorithm to trade off reward v.s. exploration at different stages of learning. In addition, we introduce a principled mechanism to terminate sample collection once we have a rich enough trajectory batch to improve the model. We rigorously evaluate our method on a variety of continuous control tasks, and demonstrate statistically significant gains over existing approaches.