It may not look like much, but this wiggly little micro-robot is surprisingly powerful and complex. Inspired by the rippling locomotion of caterpillars, physics researchers at the University of Warsaw created the robot that at first glance appears to be nothing more than a thin transparent strip. But its body is made from light sensitive elastomer aligned in a molecular pattern, the secret to its creepy-crawly movement. Exposure to light causes its body to contract in a wave-like ripple, propelling its body forward. By controlling the lighting conditions, the researchers were able to get the robot to perform different actions.

In this paper we introduce a novel framework for making exact nonparametric Bayesian inference on latent functions, that is particularly suitable for Big Data tasks. Firstly, we introduce a class of stochastic processes we refer to as string Gaussian processes (string GPs), which are not to be mistaken for Gaussian processes operating on text. We construct string GPs so that their finite-dimensional marginals exhibit suitable local conditional independence structures, which allow for scalable, distributed, and flexible nonparametric Bayesian inference, without resorting to approximations, and while ensuring some mild global regularity constraints. Furthermore, string GP priors naturally cope with heterogeneous input data, and the gradient of the learned latent function is readily available for explanatory analysis. Secondly, we provide some theoretical results relating our approach to the standard GP paradigm. In particular, we prove that some string GPs are Gaussian processes, which provides a complementary global perspective on our framework. Finally, we derive a scalable and distributed MCMC scheme for supervised learning tasks under string GP priors. The proposed MCMC scheme has computational time complexity $\mathcal{O}(N)$ and memory requirement $\mathcal{O}(dN)$, where $N$ is the data size and $d$ the dimension of the input space. We illustrate the efficacy of the proposed approach on several synthetic and real-world datasets, including a dataset with $6$ millions input points and $8$ attributes.

This paper addresses network anomography, that is, the problem of inferring network-level anomalies from indirect link measurements. This problem is cast as a low-rank subspace tracking problem for normal flows under incomplete observations, and an outlier detection problem for abnormal flows. Since traffic data is large-scale time-structured data accompanied with noise and outliers under partial observations, an efficient modeling method is essential. To this end, this paper proposes an online subspace tracking of a Hankelized time-structured traffic tensor for normal flows based on the Candecomp/PARAFAC decomposition exploiting the recursive least squares (RLS) algorithm. We estimate abnormal flows as outlier sparse flows via sparsity maximization in the underlying under-constrained linear-inverse problem. A major advantage is that our algorithm estimates normal flows by low-dimensional matrices with time-directional features as well as the spatial correlation of multiple links without using the past observed measurements and the past model parameters. Extensive numerical evaluations show that the proposed algorithm achieves faster convergence per iteration of model approximation, and better volume anomaly detection performance compared to state-of-the-art algorithms.

Efficient index structures for fast approximate nearest neighbor queries are required in many applications such as recommendation systems. In high-dimensional spaces, many conventional methods suffer from excessive usage of memory and slow response times. We propose a method where multiple random projection trees are combined by a novel voting scheme. The key idea is to exploit the redundancy in a large number of candidate sets obtained by independently generated random projections in order to reduce the number of expensive exact distance evaluations. The method is straightforward to implement using sparse projections which leads to a reduced memory footprint and fast index construction. Furthermore, it enables grouping of the required computations into big matrix multiplications, which leads to additional savings due to cache effects and low-level parallelization. We demonstrate by extensive experiments on a wide variety of data sets that the method is faster than existing partitioning tree or hashing based approaches, making it the fastest available technique on high accuracy levels.

"Seven hundred years after glasses were invented there are still 2.5 billion people in the world with poor vision and no access to vision correction," says Hong Kong philanthropist James Chen. Chairman of his family's Nigeria-based manufacturing company, Wahum Group, Chen is funding a contest called the Clearly Vision Prize that will award a total of 250,000 to projects that improve eyesight, especially in poor countries. Thirty-six semifinalists were announced this week (the five winners will be awarded September 15). Among the contenders: 3D printed eyeglass frames, drones that deliver medical supplies, and several smartphone-based technologies. Some of the smartphones help nonexperts test vision, and one uses artificial intelligence to "see" for blind people. The Clearly Vision semifinalists represent just a sampling of the smartphone projects fighting vision loss, a growing field that is bringing critical care to remote regions far from hospitals and doctors offices.

Amazon UK is to open a distribution centre at Tilbury which will be equipped with the retailer's most advanced robotics technology. When it opens in Spring 2017, the Essex-based site will be equipped with robots that slide under a tower of shelves where products are stowed, lifted and moved through the facility. The retail giant has said that the robots help speed order processing time and reduce walking time by moving the shelves to employees, as well as save space with '50 per cent more items to be stowed per square foot'. The technology was launched earlier this year at its Dunstable and Doncaster facilities. John Tagawa, Amazon's vice president of UK operations, said: "The Amazon teams are dedicated to innovating in our fulfilment centres to increase speed of delivery while enabling greater selection at lower costs for our customers. The introduction of Amazon Robotics is the newest example of our commitment to invention in logistics on behalf of our employees and our customers."

Artificial intelligence (AI) has been around for a long time and people are still waiting for the first C-3PO (a talking robot from Star Trek) to be released. Looking at the money big tech companies and venture capitalists are pouring into the sector, AI is making huge progress, although the investors are looking for different things than a talking robot. "In the long run, I think we will evolve in computing from a mobile-first to an AI-first world. And I do think we're at the forefront of developments," said Sundar Pichai, CEO of Google, Inc. on an earnings call with investors in April. Google is the most active investor in AI with 9 acquisitions completed since 2011.

It is no doubt that the sub-field of machine learning / artificial intelligence has increasingly gained more popularity in the past couple of years. As Big Data is the hottest trend in the tech industry at the moment, machine learning is incredibly powerful to make predictions or calculated suggestions based on large amounts of data. Some of the most common examples of machine learning are Netflix's algorithms to make movie suggestions based on movies you have watched in the past or Amazon's algorithms that recommend books based on books you have bought before. So if you want to learn more about machine learning, how do you start? For me, my first introduction is when I took an Artificial Intelligence class when I was studying abroad in Copenhagen. My lecturer is a full-time Applied Math and CS professor at the Technical University of Denmark, in which his research areas are logic and artificial, focusing primarily on the use of logic to model human-like planning, reasoning and problem solving.

The future can't come quickly enough for London autonomous driving startup Five.ai. The company, which raised 2.7 million in July, promises to deliver fully autonomous vehicles to the market by 2019. That's two years ahead of similar projects announced by Ford and BMW. Five.ai thinks it will beat the incumbents by using more sophisticated machine-learning that will help a vehicle understand its surroundings without the need to constantly compare its data against ultra-precise, three-dimensional maps created by radar systems, an approach being tested by Ford and Google. A vehicle running Five.ai's software, and rigged with the requisite cameras and sensors, would use a convolutional neural network to perceive an object's depth instead of relying on data from high-resolution 3D maps.

Later this month, Uber will offer the world's first ride-hailing service in Pittsburgh, using a test fleet of 100 Volvo XC90 SUVs. I admit that I didn't see it coming this fast. Only yesterday, I wrote about a new trial of self-driving minibuses in Helsinki, and it seemed pretty darn forward-looking at the time. But those vehicles are really slow, they ply the same little route repeatedly, and they stop at every stop. Today Uber is talking about driving to points specified by whoever jumps into the rear seat.