In this paper, we propose novel strategies for neutral vector variable decorrelation. Two fundamental invertible transformations, namely serial nonlinear transformation and parallel nonlinear transformation, are proposed to carry out the decorrelation. For a neutral vector variable, which is not multivariate Gaussian distributed, the conventional principal component analysis (PCA) cannot yield mutually independent scalar variables. With the two proposed transformations, a highly negatively correlated neutral vector can be transformed to a set of mutually independent scalar variables with the same degrees of freedom. We also evaluate the decorrelation performances for the vectors generated from a single Dirichlet distribution and a mixture of Dirichlet distributions. The mutual independence is verified with the distance correlation measurement. The advantages of the proposed decorrelation strategies are intensively studied and demonstrated with synthesized data and practical application evaluations.

Good sparse approximations are essential for practical inference in Gaussian Processes as the computational cost of exact methods is prohibitive for large datasets. The Fully Independent Training Conditional (FITC) and the Variational Free Energy (VFE) approximations are two recent popular methods. Despite superficial similarities, these approximations have surprisingly different theoretical properties and behave differently in practice. We thoroughly investigate the two methods for regression both analytically and through illustrative examples, and draw conclusions to guide practical application.

This paper presents a new approach, called perturb-max, for high-dimensional statistical inference that is based on applying random perturbations followed by optimization. This framework injects randomness to maximum a-posteriori (MAP) predictors by randomly perturbing the potential function for the input. A classic result from extreme value statistics asserts that perturb-max operations generate unbiased samples from the Gibbs distribution using high-dimensional perturbations. Unfortunately, the computational cost of generating so many high-dimensional random variables can be prohibitive. However, when the perturbations are of low dimension, sampling the perturb-max prediction is as efficient as MAP optimization. This paper shows that the expected value of perturb-max inference with low dimensional perturbations can be used sequentially to generate unbiased samples from the Gibbs distribution. Furthermore the expected value of the maximal perturbations is a natural bound on the entropy of such perturb-max models. A measure concentration result for perturb-max values shows that the deviation of their sampled average from its expectation decays exponentially in the number of samples, allowing effective approximation of the expectation.

We consider a stochastic continuum armed bandit problem where the arms are indexed by the $\ell_2$ ball $B_{d}(1+\nu)$ of radius $1+\nu$ in $\mathbb{R}^d$. The reward functions $r :B_{d}(1+\nu) \rightarrow \mathbb{R}$ are considered to intrinsically depend on $k \ll d$ unknown linear parameters so that $r(\mathbf{x}) = g(\mathbf{A} \mathbf{x})$ where $\mathbf{A}$ is a full rank $k \times d$ matrix. Assuming the mean reward function to be smooth we make use of results from low-rank matrix recovery literature and derive an efficient randomized algorithm which achieves a regret bound of $O(C(k,d) n^{\frac{1+k}{2+k}} (\log n)^{\frac{1}{2+k}})$ with high probability. Here $C(k,d)$ is at most polynomial in $d$ and $k$ and $n$ is the number of rounds or the sampling budget which is assumed to be known beforehand.

Anticipation is growing for the July release of Tesla's'affordable' $35,000 Model 3. Now, the latest shots of Telsa testing the car may have revealed one of its final secrets - what the interior will look like. The shots, taken near Tesla's headquarters in Palo Alto, California, reveal the car has a single screen and no traditional instruments. Musk had previously addressed the issue of no traditional dashboard display, tell users who asked for one'You won't care' before confirming the car won't use a heads up display either. A new comparison of models on Tesla's own site confirms the spec, saying the Model 3 will only have a single 15inch display, while the more expensive Model S has a separate'driver display'. According to Teslerati, 'The latest photos gives us a clearer look at the landscape-mounted touchscreen, which resembles an off-the-shelf computer monitor that's been bolted onto the dashboard.'

Amazon provides an enormously rich and interesting variety of robotics use cases. If you are enthusiastic about problem-driven robotics research, if you want your work to have massive impact on how robotics will change our world, Amazon is the place to be for you. Amazon has launched a new Robotics team in Berlin, focusing on Machine Learning and AI methods for robotics. The goals include generic robot manipulation, but also long-term strategic research towards robotic AI beyond factories. The team is part of the Core Machine Learning team in Berlin, which is a method development oriented lab with world-leading experts in the field.

Hundreds of AI researchers have taken a glimpse into their crystal balls to try to determine when machines will finally exceed human capabilities. A survey run by the Future of Humanity Institute, a research center that studies existential risks at the University of Oxford in the UK and Yale University in the US, asked 352 machine learning researchers to predict how AI will progress. "Researchers believe there is a 50 per cent chance of AI outperforming humans in all tasks in 45 years and of automating all human jobs in 120 years," according to the results published on arXiv. It's a tricky question and opinions vary wildly. Elon Musk and Stephen Hawking have been vocal about humanity's doom at AI takeover, whereas researchers like Andrew Ng, former chief scientist at Baidu, and Oren Etzioni, CEO of the Allen Institute for Artificial Intelligence, have a more conservative attitude. The survey asks the question: "When will AI exceed human performance?"

A robot priest that beams lights from its hands is giving'auto-blessings' in the same German city where Martin Luther launched the Protestant Reformation. Five hundred years after Luther published the 95 Theses in the town of Wittenberg, in the state of Saxony-Anhalt, an evangelical church unveiled an automatic blessing robot for the special celebrations. The robot on show is called'BlessU-2' and was developed by the Evangelical Church in Hesse and Nassau. It consists of a metal box with a touch screen, two arms, a head with electronic eyes and a digital mouth. A robot priest that beams lights from its hands is giving'auto-blessings' in the same German city where Martin Luther launched the Protestant Reformation After the robot wishes users a'warm welcome', it asks if they want to be blessed by a male or female voice.

Technology moves at breakneck speed, and we now have more power in our pockets than we had in our homes in the 1990s. Augmented reality (AR) has been a fascinating concept of science fiction for decades, but many researchers think we're finally getting close to making AR a reality thanks to advancements in computer vision. By definition, computer vision is a field that includes methods for acquiring, processing, analyzing, and understanding images and, in general, high-dimensional data from the real world in order to produce numerical or symbolic information, e.g., in the forms of decisions. In layman's terms, computer visions allows machines to recognize and understand sight – just as humans can. This means that with AR, you can process image and video sources to extract meaningful information and take action based on that.

Sony's attempt at introducing Virtual Reality to millions of homes has been quite impressive, the device having sold unexpectedly big numbers. However, console accessories often fail to continuously sell without a'killer app'. For instance, the Nintendo Switch's reasonably rubbish release line-up was improved phenomenally by Zelda: Breath of the Wind, the console selling by the millions as a result. So far, the best VR-only experiences have been Batman, Rigs, and REZ (Resident Evil VII was playable in VR but better played as a normal console game) but none have been'must-play' games. Packaged with the Aim controller, this first-person shooter has potential but bores relatively quickly.