While it's always possible to compute a variational approximation to a posterior distribution, it can be difficult to discover problems with this approximation". We propose two diagnostic algorithms to alleviate this problem. The Pareto-smoothed importance sampling (PSIS) diagnostic gives a goodness of fit measurement for joint distributions, while simultaneously improving the error in the estimate.

Correlated component analysis as proposed by Dmochowski et al. (2012) is a tool for investigating brain process similarity in the responses to multiple views of a given stimulus. Correlated components are identified under the assumption that the involved spatial networks are identical. Here we propose a hierarchical probabilistic model that can infer the level of universality in such multi-view data, from completely unrelated representations, corresponding to canonical correlation analysis, to identical representations as in correlated component analysis. This new model, which we denote Bayesian correlated component analysis, evaluates favourably against three relevant algorithms in simulated data. A well-established benchmark EEG dataset is used to further validate the new model and infer the variability of spatial representations across multiple subjects.

The Wallenius distribution is a generalisation of the Hypergeometric distribution where weights are assigned to balls of different colours. This naturally defines a model for ranking categories which can be used for classification purposes. Since, in general, the resulting likelihood is not analytically available, we adopt an approximate Bayesian computational (ABC) approach for estimating the importance of the categories. We illustrate the performance of the estimation procedure on simulated datasets. Finally, we use the new model for analysing two datasets about movies ratings and Italian academic statisticians' journal preferences. The latter is a novel dataset collected by the authors.

Scientific disciplines, such as Behavioural Psychology, Anthropology and recently Social Signal Processing are concerned with the systematic exploration of human behaviour. A typical work-flow includes the manual annotation (also called coding) of social signals in multi-modal corpora of considerable size. For the involved annotators this defines an exhausting and time-consuming task. In the article at hand we present a novel method and also provide the tools to speed up the coding procedure. To this end, we suggest and evaluate the use of Cooperative Machine Learning (CML) techniques to reduce manual labelling efforts by combining the power of computational capabilities and human intelligence. The proposed CML strategy starts with a small number of labelled instances and concentrates on predicting local parts first. Afterwards, a session-independent classification model is created to finish the remaining parts of the database. Confidence values are computed to guide the manual inspection and correction of the predictions. To bring the proposed approach into application we introduce NOVA - an open-source tool for collaborative and machine-aided annotations. In particular, it gives labellers immediate access to CML strategies and directly provides visual feedback on the results. Our experiments show that the proposed method has the potential to significantly reduce human labelling efforts.

This is a guest post. The views expressed here are solely those of the author and do not represent positions of IEEE Spectrum or the IEEE. This week my colleague Dieter Vanderelst presented our paper: "The Dark Side of Ethical Robots" at AIES 2018 in New Orleans. I blogged about Dieter's very elegant experiment here, but let me summarize. With two NAO robots he set up a demonstration of an ethical robot helping another robot acting as a proxy human, then showed that with a very simple alteration of the ethical robot's logic it is transformed into a distinctly unethical robot--behaving either competitively or aggressively toward the proxy human.

Everybody seems to be talking about artificial intelligence and machine learning. Ever since Spielberg's 2001 movie A.I. Artificial Intelligence, the abbreviation AI has been readily recognizable. News outlets have recently carried headlines such as, "AI in your car can brake faster than you", or "Police use AI to predict crime", or similar flashy statements. But then you may also read about machine learning algorithms that can convert a 2D image to 3D or have learned the grammar of a language. After reading all that, you may try to explain these interesting advancements to your technically savvy friends.

"The sensationalist coverage these stories receive isn't very helpful and obscures the main issues," author Chris Middleton told Sputnik. "We're not talking about C-3P0 sitting at your desk, we're talking about smart devices, industrial machines, drones, autonomous vehicles, plus software that automates technology." Accountancy firm PwC analysed 200,000 jobs across 29 countries and suggests the first wave of job losses will begin in the early 2020s. "When you look at financial services, a lot of jobs are relatively routine jobs such as data analysis," said PwC chief economist John Hawksworth who suggests the closure of bank branches is indicative of the current situation. Around six and eight percent of positions in the financial sector could be lost because "a lot of jobs are relatively routine jobs such as data analysis," he said.

Back in mid-2015, Turing Robotics Industries unveiled its delightfully quirky debut smartphone, an encrypted Android device encased in colorful chrome. Though we cautioned that it could be delayed for a myriad of reasons that often plague small companies, we looked forward to their release in December...then delayed until early 2016...and long story short, it didn't ship at all. Now the company is filing for bankruptcy in Salo, Finland where it had rented a warehouse for manufacturing. But not to worry, Turing Robotics CEO Steve Chao assured customers in a Facebook post: That doesn't mean the company is actually bankrupt. Finnish publication Salon Seudon Sanomat broke the news of the company's financial issues, reporting that creditors had filed a claim with Turing Robotics last year leading to the seizure of its movable property.

In the twenty-first century century we will see a fundamental shift in the relationship between human and machines. Robots can now learn, perceive the world around them, and interact with people. Professor Dario Floreano is one of the world's leading experts in robotics and artificial intelligence. He is Director of the Laboratory of Intelligent Systems at the Swiss Federal Institute of Technology in Lausanne and is Director of the Swiss National Centre of Competence in Robotics. Professor Floreano is also a founding member of the World Economic Forum's Global Agenda Council on Robotics and Smart Devices and is an executive board member of the International Society for Neural Networks.

Ever yearned to chisel a sculpture, compose a symphony or design a gigantic neon metropolis? Tue 6 Feb 2018 11.38 EST Last modified on Tue 6 Feb 2018 11.42 EST Most homes hide abandoned easels, guitars and origami kits, all bought with good intentions to express the latent creativity that grownup life can easily stifle. You might want to unlock it, but the effort is too intimidating. Media Molecule, a game developer based in Guildford, believes that video games can help. A studio populated by artists, musicians and creatives of all stripes, it is best known for the successful LittleBigPlanet games – cheerful adventures with a hand-crafted look and a novel "play, create, share" philosophy, letting players remix the levels and make their own.