In this technical report, we discuss several sampling algorithms for Determinantal Point Processes (DPP). DPPs have recently gained a broad interest in the machine learning and statistics literature as random point processes with negative correlation, i.e., ones that can generate a "diverse" sample from a set of items. They are parametrized by a matrix $\mathbf{L}$, called $L$-ensemble, that encodes the correlations between items. The standard sampling algorithm is separated in three phases: 1/~eigendecomposition of $\mathbf{L}$, 2/~an eigenvector sampling phase where $\mathbf{L}$'s eigenvectors are sampled independently via a Bernoulli variable parametrized by their associated eigenvalue, 3/~a Gram-Schmidt-type orthogonalisation procedure of the sampled eigenvectors. In a naive implementation, the computational cost of the third step is on average $\mathcal{O}(N\mu^3)$ where $\mu$ is the average number of samples of the DPP. We give an algorithm which runs in $\mathcal{O}(N\mu^2)$ and is extremely simple to implement. If memory is a constraint, we also describe a dual variant with reduced memory costs. In addition, we discuss implementation details often missing in the literature.

Implicit models, which allow for the generation of samples but not for point-wise evaluation of probabilities, are omnipresent in real-world problems tackled by machine learning and a hot topic of current research. Some examples include data simulators that are widely used in engineering and scientific research, generative adversarial networks (GANs) for image synthesis, and hot-off-the-press approximate inference techniques relying on implicit distributions. The majority of existing approaches to learning implicit models rely on approximating the intractable distribution or optimisation objective for gradient-based optimisation, which is liable to produce inaccurate updates and thus poor models. This paper alleviates the need for such approximations by proposing the Stein gradient estimator, which directly estimates the score function of the implicitly defined distribution. The efficacy of the proposed estimator is empirically demonstrated by examples that include meta-learning for approximate inference, and entropy regularised GANs that provide improved sample diversity.

In many natural language processing tasks the words and the documents are represented using the "bag of words" model. In such a model, a document is represented by a high-dimensional vector, with the components corresponding to the frequency of a particular word in the document (for a detailed discussion see [1-3] and the references within). For example, assuming an English vocabulary of 25, 000 words, each document will be represented by a 25, 000 dimensional vector, where the component i is the frequency of the ith word in the document. The vector representation is particularly useful in text classification tasks, where the similarity of two documents can be simply estimated using the dot product between the vectors. If the vectors are normalized, then their dot product is equal to the cosine of the angle between the vectors, and therefore the more parallel the vectors are, the more similar the documents are.

A subsidiary of British banking giant Royal Bank of Scotland (RBS) is running a pilot program using an artificial intelligence (AI) powered "digital human" to help customers with basic banking questions. The lifelike, virtual bank teller named "Cora" can answer up to 200 banking queries for NatWest customers in two-way conversations on a computer screen, tablet or mobile phone. The bank has been using Cora since 2017 and she's had about 100,000 conversations a month, the bank said on Wednesday. "Cora, the digital human is able to answer basic verbal questions like'How do I login to online banking?' 'How do I apply for a mortgage?' and'What do I do if I lose my card?'" said NatWest in a news release. Cora's human-like appearance includes ear piercings and facial expressions.

The healthcare industry is in the middle of a revolution, social media is getting smarter, and the era of drone-wielding super villains is right around the corner. Earlier this week seven of the world's most prominent organizations in the field of futurism published a report predicting the dangers posed by AI. The document is called "The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation." You can read the full version here. The only thing that could make it scarier is if Samuel L. Jackson were holding you at gunpoint and screaming it at you.

It's been a typical week for typical college student BINA48. On Monday, BINA attended her robot ethics class. On Tuesday, the second-semester student had an excused absence to ring the bell at the stock exchange, and soon BINA will be assistant-teaching a kindergarten class and getting a face-lift at Hanson Robotics. But that hasn't stopped the robot, which looks like the bust of a flesh-and-blood woman, from completing a Philosophy of Love course at Notre Dame de Namur University in Belmont, California. Programmed to be social, BINA48 presented her final project along with a human student, demonstrating that the robot could retain and present a philosophical perspective on love.

Experts at the University of Cambridge have warned that rogue states and terrorists could turn to artificial intelligence (AI) to destabilise the world. A new report by 26 experts on AI, security and technology suggests that unless preparations are made against the malicious use of the technology, cybercrime will rapidly increase in years to come. The report, The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation, also warns of the rise of "highly believable fake videos" impersonating prominent figures or faking events to manipulate public opinion around political events. It forecasts artificially intelligent bots being used to manipulate the news agenda, social media and elections as well as the hijacking of drones and autonomous vehicles. AI software features prominently in modern life - it is used to power virtual assistants such as Amazon's Alexa and many smartphone features, as well as in driverless car technology and on an industrial scale to process large amounts of data.

Advances in artificial intelligence have the potential to supercharge medical research and better detect diseases, but it could also amplify the actions of bad actors. That's according to a report released this week by a team of academics and researchers from Oxford University, Cambridge University, Stanford University, the Electronic Frontier Foundation, artificial intelligence research group OpenAI, and others institutes. The report's authors aren't concerned with sci-fi doomsday scenarios like robots taking over the world, such as in Terminator, but more practical concerns. Criminals, for instance, could use machine learning technologies to further automate hacking attempts, putting more pressure on already beleaguered corporate security officers to ensure their computer systems are safe. The goal of the report is not to dissuade companies, researchers, or the public from AI, but to highlight the most realistic concerns so people can better prepare and possibly prevent future cyber attacks or other problems related to AI.

When arrested, Mohammed already had two of the ingredients needed to make the highly unstable TATP (acetone peroxide), known as the "mother of Satan", which was used by a suicide bomber in an attack on a pop concert at the Manchester Arena last May, killing 22 children and adults.

The robotics work programme implements the robotics strategy developed by SPARC, the Public-Private Partnership for Robotics in Europe (see the Strategic Research Agenda). EuRobotics regularly publishes video interviews with projects, so that you can find out more about their activities. You can also see many of these projects at the upcoming European Robotics Forum (ERF) in Tampere Finland March 13-15. Make ROS-Industrial the open-source industrial standard for intelligent industrial robots, and put Europe in a leading position within this global initiative. Presently, potential users are waiting for improved quality and quantity of ROS-Industrial components, but both can improve only when more parties contribute and use ROS-Industrial.