In a village in western Africa, a tsetse fly bites a human, injecting a swarm of the deadly sleeping sickness-causing parasite Trypanosoma brucei into the bloodstream. Once inside its human host, the parasite spreads through the body, rapidly using its flexible flagellum to propel itself, eventually hiding the structure inside its body to evade the host's immune system once it is safely ensconced. Imagine a swarm of microscopic bots that mimics Trypanosoma brucei's behavior. In this case, though, instead of killing their hosts, the bots are designed to circulate through the bloodstream to perform highly-targeted drug deliveries and carry out invasive and delicate surgeries that may otherwise be too risky to perform. This is what a team of scientists at the Swiss Federal Institute of Technology in Zurich (ETHZ) and the Swiss Federal Institute of Technology in Lausanne (EPFL) are working toward.

The 2011 triumph of IBM's Watson supercomputer in US game show, Jeopardy, was the moment it became a real-world commercial venture within the enterprise services giant. The question-answering system, named in honour of IBM's first CEO, Thomas J Watson, defeated two former winners of the show, Brad Rutter and Ken Jennings, to clinch a 1 million prize, using onboard (rather than cloud-based) data. IBM began offering Watson as a cloud service in 2015, and since then the company has found itself at the centre of a range of new, speculative ventures. As we will explore, some of these blur the lines between classical computing, AI, and machine learning, and may point towards a networked future for humanoid robots. Duncan Anderson, IBM's European CTO of the Watson Program, picks up the story: We started to think about how we could make the Watson technology more consumable and less resource intensive.

As artificial intelligence and social robotics begin to replace tasks and jobs originally held by highly-trained humans we are entering the uncharted waters of the fourth industrial revolution, or "second machine age". The new machines are very much unlike their predecessors because of they are able to learn. They can thus evolve over time to become better and increase their performance. Optimists suggest that by taking over cognitive but labour-intensive chores the intelligent machines will free human workers to do more "creative" tasks; and by working side by side with us they will boost our imagination to achieve more, using their power for detail, ability to rapidly analyse massive data, and lack of psychological bias. But what is often missing from the current debate are the social and economic roles of companies as employers.

Australian bank Westpac is to trial the use of artificial intelligence (AI) in its digital banking systems, as it looks to automate customers' queries. With the rise of digital banking, Westpac's general manager of consumer digital, Travis Tyler, says it is looking at using "bots" to respond to customers' simple questions. One example includes the bank working on a "proof of concept" over the next six months for a digital system to provide answers to consumer questions about the best deposit rates available. In an interview with the Sydney Morning Herald, Tyler says: "If your term deposit is rolling over, and you simply ask, 'What's the best rate, this is what I want to achieve?', it will come back with the best options and you can simply say, 'Yeah, book it.'" Another example cited by Tyler includes answering simple questions about payments between accounts.

As headlines go, "Brexit leads to robot takeover" sounds like satire. It's up there with Brexit being "the opportunity to create a second Elizabethan Golden Age". Both have been written recently – but I would argue that the former may actually be true. Recessions force companies to make difficult choices to survive. One of the first places to cut costs is the wage bill.

We all have a soft spot for Prisma, the app that turns smartphone photos into stylized artwork. But the reverse process -- transforming artwork into pictures -- is no less fascinating. And it's not far from becoming real, researchers in the Netherlands said. A team of four neuroscientists at Radboud University is working on a model for inverting face sketches to synthesize photorealistic face images by using deep neural networks. The results of the study (Convolutional Sketch Inversion) were first made available in the online archive arXiv and have recently been accepted at the European Conference on Computer Vision in Amsterdam.

Like the Tin Man in The Wizard Of Oz, the robot community has finally found its heart. This time around it's not made of sawdust-stuffed silk. Better -- sensors, cameras, microphones and proprietary algorithms that calculate human emotion according to vocal intonation and facial expressions. And soon it could be ambling around your home, asking if you feel alright, after it goes on sale in Japan from F span class "s1" ebruary 2015 for 198,000 yen ( 1,151.99). Pepper is a Wi-Fi enabled humanoid robot that weighs 28kg, features a 10.1-inch touchscreen and can move at speeds of up to 3km/h.

In the late 1700s, machinists started making music boxes: intricate little mechanisms that could play harmonies and melodies by themselves. Some incorporated bells, drums, organs, even violins, all coordinated by a rotating cylinder. The more ambitious examples were Lilliputian orchestras, such as the Panharmonicon, invented in Vienna in 1805, or the mass-produced Orchestrion that came along in Dresden in 1851. But the technology had limitations. To make a convincing violin sound, one had to create a little simulacrum of a violin -- quite an engineering feat. How to replicate a trombone? The artisans assumed that an entire instrument had to be copied in order to capture its distinctive tone. The metal, the wood, the reed, the shape, the exact resonance, all of it had to be mimicked. How else were you going to create an orchestral sound?

We consider clustering problems where the goal is to determine an optimal partition of a given point set in Euclidean space in terms of a collection of affine subspaces. While there is vast literature on heuristics for this kind of problem, such approaches are known to be susceptible to poor initializations and getting trapped in bad local optima. We alleviate these issues by introducing a semidefinite relaxation based on Lasserre's method of moments. While a similiar approach is known for classical Euclidean clustering problems, a generalization to our more general subspace scenario is not straightforward, due to the high symmetry of the objective function that weakens any convex relaxation. We therefore introduce a new mechanism for symmetry breaking based on covering the feasible region with polytopes. Additionally, we introduce and analyze a deterministic rounding heuristic.

Consider the stochastic composition optimization problem where the objective is a composition of two expected-value functions. We propose a new stochastic first-order method, namely the accelerated stochastic compositional proximal gradient (ASC-PG) method, which updates based on queries to the sampling oracle using two different timescales. The ASC-PG is the first proximal gradient method for the stochastic composition problem that can deal with nonsmooth regularization penalty. We show that the ASC-PG exhibits faster convergence than the best known algorithms, and that it achieves the optimal sample-error complexity in several important special cases. We further demonstrate the application of ASC-PG to reinforcement learning and conduct numerical experiments.