Researchers from the Nanyang Technological Institute in Singapore, Malaysia have managed to control the flight paths of adult male M. torquata beetles by implanting electrodes into four of their flight muscles and controlling them with tiny backpacks. The insects have essentially been turned into'soft robots' by embedding them with artificial devices. Researchers in Malaysia have managed to control the flight paths of adult male M. torquata beetles by implanting electrodes into four of their flight muscles The researchers used electric pulses to steer them in different directions, and their acceleration could be increased by changing the frequency of the pulses. 'Instead of imitating the complicated kinetics and mechanisms of insect locomotion, a live insect can be directly transformed into a soft robot by embedding it with artificial devices,' the study, published in the Soft Robotics journal, explained. 'This is the first demonstration that insect motion can be steered in a desired direction in a consistent way,' Sawyer Fuller from the University of Washington in Seattle, who is not involved with the research, said to New Scientist.

We propose a generic, Bayesian, information geometric approach to the exploration--exploitation trade-off in multi-armed bandit problems. Our approach, BelMan, uniformly supports pure exploration, exploration--exploitation, and two-phase bandit problems. The knowledge on bandit arms and their reward distributions is summarised by the barycentre of the joint distributions of beliefs and rewards of the arms, the \emph{pseudobelief-reward}, within the beliefs-rewards manifold. BelMan alternates \emph{information projection} and \emph{reverse information projection}, i.e., projection of the pseudobelief-reward onto beliefs-rewards to choose the arm to play, and projection of the resulting beliefs-rewards onto the pseudobelief-reward. It introduces a mechanism that infuses an exploitative bias by means of a \emph{focal distribution}, i.e., a reward distribution that gradually concentrates on higher rewards. Comparative performance evaluation with state-of-the-art algorithms shows that BelMan is not only competitive but can also outperform other approaches in specific setups, for instance involving many arms and continuous rewards.

This paper presents a brief introduction to the key points of the Grey Machine Learning (GML) based on the kernels. The general formulation of the grey system models have been firstly summarized, and then the nonlinear extension of the grey models have been developed also with general formulations. The kernel implicit mapping is used to estimate the nonlinear function of the GML model, by extending the nonparametric formulation of the LSSVM, the estimation of the nonlinear function of the GML model can also be expressed by the kernels. A short discussion on the priority of this new framework to the existing grey models and LSSVM have also been discussed in this paper. And the perspectives and future orientations of this framework have also been presented.

Electroencephalogram, an influential equipment for analyzing humans activities and recognition of seizure attacks can play a crucial role in designing accurate systems which can distinguish ictal seizures from regular brain alertness, since it is the first step towards accomplishing a high accuracy computer aided diagnosis system (CAD). In this article a novel approach for classification of ictal signals with wavelet based cross frequency coupling (CFC) is suggested. After extracting features by wavelet based CFC, optimal features have been selected by t-test and quadratic discriminant analysis (QDA) have completed the Classification.

Computed tomography (CT) is a popular medical imaging modality in clinical applications. At the same time, the x-ray radiation dose associated with CT scans raises public concerns due to its potential risks to the patients. Over the past years, major efforts have been dedicated to the development of Low-Dose CT (LDCT) methods. However, the radiation dose reduction compromises the signal-to-noise ratio (SNR), leading to strong noise and artifacts that down-grade CT image quality. In this paper, we propose a novel 3D noise reduction method, called Structure-sensitive Multi-scale Generative Adversarial Net (SMGAN), to improve the LDCT image quality. Specifically, we incorporate three-dimensional (3D) volumetric information to improve the image quality. Also, different loss functions for training denoising models are investigated. Experiments show that the proposed method can effectively preserve structural and texture information from normal-dose CT (NDCT) images, and significantly suppress noise and artifacts. Qualitative visual assessments by three experienced radiologists demonstrate that the proposed method retrieves more detailed information, and outperforms competing methods.

The web link selection problem is to select a small subset of web links from a large web link pool, and to place the selected links on a web page that can only accommodate a limited number of links, e.g., advertisements, recommendations, or news feeds. Despite the long concerned click-through rate which reflects the attractiveness of the link itself, the revenue can only be obtained from user actions after clicks, e.g., purchasing after being directed to the product pages by recommendation links. Thus, the web links have an intrinsic \emph{multi-level feedback structure}. With this observation, we consider the context-free web link selection problem, where the objective is to maximize revenue while ensuring that the attractiveness is no less than a preset threshold. The key challenge of the problem is that each link's multi-level feedbacks are stochastic, and unobservable unless the link is selected. We model this problem with a constrained stochastic multi-armed bandit formulation, and design an efficient link selection algorithm, called Constrained Upper Confidence Bound algorithm (\textbf{Con-UCB}), and prove $O(\sqrt{T\ln T})$ bounds on both the regret and the violation of the attractiveness constraint. We conduct extensive experiments on three real-world datasets, and show that \textbf{Con-UCB} outperforms state-of-the-art context-free bandit algorithms concerning the multi-level feedback structure.

We study the problem of sampling from a distribution where the negative logarithm of the target density is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially non-convex inside this ball. We study both overdamped and underdamped Langevin MCMC and prove upper bounds on the time required to obtain a sample from a distribution that is within $\epsilon$ of the target distribution in $1$-Wasserstein distance. For the first-order method (overdamped Langevin MCMC), the time complexity is $\tilde{\mathcal{O}}\left(e^{cLR^2}\frac{d}{\epsilon^2}\right)$, where $d$ is the dimension of the underlying space. For the second-order method (underdamped Langevin MCMC), the time complexity is $\tilde{\mathcal{O}}\left(e^{cLR^2}\frac{\sqrt{d}}{\epsilon}\right)$ for some explicit positive constant $c$. Surprisingly, the convergence rate is only polynomial in the dimension $d$ and the target accuracy $\epsilon$. It is however exponential in the problem parameter $LR^2$, which is a measure of non-logconcavity of the target distribution.

More than 300 million people around the world depend on drinking water extracted from the sea, but turning saltwater into freshwater isn't always efficient. Computer pioneer Alan Turing had an idea more than 50 years ago that is just now being put to use to improve the process. Two basic desalination methods exist: boil sea water and collect the evaporated pure water, or pump sea water through membranes that extract the salt. This process, called reverse osmosis, is favoured everywhere except in the Middle East, where boiling is cheaper.

A fashion designer working on a new collection has an idea, but wonders if it's been done before. Another is looking for historical inspiration--1950s-style wasp waists or 80s-era padded shoulders. The suite of AI tools IBM is developing for the fashion industry can take a photo of a dress or a shirt and search for similar garments. It can search for images with specific elements--Mandarin collars, for example, or gladiator laces, or fleur-de-lis prints. It can also design patterns itself, based on any image data set a user inputs--architectural images, amoebas, sunsets. "Fashion designers arduously put in efforts and time in coming up with new designs which could potentially be trend-setters," says Priyanka Agrawal, a research scientist at IBM Research India, who has worked on Cognitive Prints.

Intel is deploying hi-tech drones to help spot parts of the Great Wall of China that have fallen into disrepair. The chipmaker is sending some Falcon 8 drones to shoot aerial photos of the famous Jiankou section of the wall, which is known for its steep climbs and scenic views. Due to its thick vegetation and centuries old materials, the areas has'naturally weathered' and requires repair -- a process that can be made easier by using drones, Intel said. Intel, which is partnering with the China Foundation for Cultural Heritage Conservation for the project, will send its Falcon drones to take aerial photos that will then be converted into high-definition images. Artificial intelligence will create a visual representation of the Great Wall to identify areas that are in need of repair and plan the safest way to restore them.