We study the convergence of the graph Laplacian of a random geometric graph generated by an i.i.d. sample from a $m$-dimensional submanifold $M$ in $R^d$ as the sample size $n$ increases and the neighborhood size $h$ tends to zero. We show that eigenvalues and eigenvectors of the graph Laplacian converge with a rate of $O\Big(\big(\frac{\log n}{n}\big)^\frac{1}{2m}\Big)$ to the eigenvalues and eigenfunctions of the weighted Laplace-Beltrami operator of $M$. No information on the submanifold $M$ is needed in the construction of the graph or the "out-of-sample extension" of the eigenvectors. Of independent interest is a generalization of the rate of convergence of empirical measures on submanifolds in $R^d$ in infinity transportation distance.

Artificial Intelligence is a central topic in the computer science curriculum. From the year 2011 a project-based learning methodology based on computer games has been designed and implemented into the intelligence artificial course at the University of the Bio-Bio. The project aims to develop software-controlled agents (bots) which are programmed by using heuristic algorithms seen during the course. This methodology allows us to obtain good learning results, however several challenges have been founded during its implementation. In this paper we show how linguistic descriptions of data can help to provide students and teachers with technical and personalized feedback about the learned algorithms. Algorithm behavior profile and a new Turing test for computer games bots based on linguistic modelling of complex phenomena are also proposed in order to deal with such challenges. In order to show and explore the possibilities of this new technology, a web platform has been designed and implemented by one of authors and its incorporation in the process of assessment allows us to improve the teaching learning process.

Clustering is inherently ill-posed: there often exist multiple valid clusterings of a single dataset, and without any additional information a clustering system has no way of knowing which clustering it should produce. This motivates the use of constraints in clustering, as they allow users to communicate their interests to the clustering system. Active constraint-based clustering algorithms select the most useful constraints to query, aiming to produce a good clustering using as few constraints as possible. We propose COBRA, an active method that first over-clusters the data by running K-means with a $K$ that is intended to be too large, and subsequently merges the resulting small clusters into larger ones based on pairwise constraints. In its merging step, COBRA is able to keep the number of pairwise queries low by maximally exploiting constraint transitivity and entailment. We experimentally show that COBRA outperforms the state of the art in terms of clustering quality and runtime, without requiring the number of clusters in advance.

We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers. We use a deep feed-forward neural network trained with load-flows precomputed by simulation. Our architecture permits to train a network on so-called "n-1" problems, in which load flows are evaluated for every possible line disconnection, then generalize to "n-2" problems without retraining (a clear advantage because of the combinatorial nature of the problem). To that end, we developed a technique bearing similarity with "dropout", which we named "guided dropout".

Generative adversarial networks (GANs) evolved into one of the most successful unsupervised techniques for generating realistic images. Even though it has recently been shown that GAN training converges, GAN models often end up in local Nash equilibria that are associated with mode collapse or otherwise fail to model the target distribution. We introduce Coulomb GANs, which pose the GAN learning problem as a potential field of charged particles, where generated samples are attracted to training set samples but repel each other. The discriminator learns a potential field while the generator decreases the energy by moving its samples along the vector (force) field determined by the gradient of the potential field. Through decreasing the energy, the GAN model learns to generate samples according to the whole target distribution and does not only cover some of its modes. We prove that Coulomb GANs possess only one Nash equilibrium which is optimal in the sense that the model distribution equals the target distribution. We show the efficacy of Coulomb GANs on a variety of image datasets. On LSUN and celebA, Coulomb GANs set a new state of the art and produce a previously unseen variety of different samples.

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. RobMoSys will coordinate the whole community's best and consorted efforts to realize a step-change towards an industry-grade software development ecosystem. RobMoSys envisions a model-driven integration approach built around the current code-centric robotic platforms.

It is easy to confuse the current geopolitical situation with that of the 1980s. The United States and Russia each accuse the other of interfering in domestic affairs. Russia has annexed territory over U.S. objections, raising concerns about military conflict. As during the Cold War after World War II, nations are developing and building weapons based on advanced technology. During the Cold War, the weapon of choice was nuclear missiles; today it's software, whether its used for attacking computer systems or targets in the real world. Russian rhetoric about the importance of artificial intelligence is picking up – and with good reason: As artificial intelligence software develops, it will be able to make decisions based on more data, and more quickly, than humans can handle.

Workers in Mansfield, Sunderland and Wakefield are at the highest risk of having their jobs taken by machines, according to a report warning that automation stands to further widen the north-south divide. Outside of the south of England, one in four jobs are at risk of being replaced by advances in technology – much higher than the 18% average for wealthier locations closer to London. Struggling towns and cities in the north and the Midlands are most exposed. A total of 3.6m UK jobs could be replaced by machines. The Centre for Cities thinktank says almost one-third of the jobs in the Nottinghamshire town of Mansfield, which is home to the Sports Direct warehouse, are involved in lines of work under threat as robots begin to replace humans in the years up to 2030.

One in five jobs in British cities is likely to be displaced by 2030 because of automation and globalisation, a new report predicts. Retail, customer service and warehouse jobs are among those most at threat of being lost, said Centre for Cities. The think tank said struggling cities in the North and Midlands were more exposed to job losses than wealthier cities in the South, compounding the North/South divide. Cities including Mansfield, Sunderland and Wakefield could see two out of five jobs lost, while Oxford and Cambridge face losing 13%, the study found. The report said the changes would lead to jobs being created as well as lost, but in Northern and Midlands' cities they would largely be in low-skilled occupations.

ACM Student Chapter Munich 18,742 views Jurgen Schmidhuber "Universal AI and a Formal Theory of Fun" - Duration: 47:22.