In this case, the user performed an image search for nanoparticles. As scientific datasets increase in both size and complexity, the ability to label, filter and search this deluge of information has become a laborious, time-consuming and sometimes impossible task, without the help of automated tools. With this in mind, a team of researchers from the Department of Energy's Lawrence Berkeley National Laboratory (Berkeley Lab) and UC Berkeley are developing innovative machine learning tools to pull contextual information from scientific datasets and automatically generate metadata tags for each file. Scientists can then search these files via a web-based search engine for scientific data, called Science Search, that the Berkeley team is building. As a proof-of-concept, the team is working with staff at Berkeley Lab's Molecular Foundry, to demonstrate the concepts of Science Search on the images captured by the facility's instruments.

Attacks against the control processor of a power-grid system, especially zero-day attacks, can be catastrophic. Earlier detection of the attacks can prevent further damage. However, detecting zero-day attacks can be challenging because they have no known code and have unknown behavior. In order to address the zero-day attack problem, we propose a data-driven defense by training a temporal deep learning model, using only normal data from legitimate processes that run daily in these power-grid systems, to model the normal behavior of the power-grid controller. Then, we can quickly find malicious codes running on the processor, by estimating deviations from the normal behavior with a statistical test. Experimental results on a real power-grid controller show that we can detect anomalous behavior with over 99.9% accuracy and nearly zero false positives.

Deep Gaussian Processes (DGPs) are hierarchical generalizations of Gaussian Processes that combine well calibrated uncertainty estimates with the high flexibility of multilayer models. One of the biggest challenges with these models is that exact inference is intractable. The current state-of-the-art inference method, Variational Inference (VI), employs a Gaussian approximation to the posterior distribution. This can be a potentially poor unimodal approximation of the generally multimodal posterior. In this work, we provide evidence for the non-Gaussian nature of the posterior and we apply the Stochastic Gradient Hamiltonian Monte Carlo method to directly sample from it. To efficiently optimize the hyperparameters, we introduce the Moving Window MCEM algorithm. This results in significantly better predictions at a lower computational cost than its VI counterpart. Thus our method establishes a new state-of-the-art for inference in DGPs.

In this paper, we propose multi-variable LSTM capable of accurate forecasting and variable importance interpretation for time series with exogenous variables. Current attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To this end, the multi-variable LSTM equipped with tensorized hidden states is developed to learn hidden states for individual variables, which give rise to our mixture temporal and variable attention. Based on such attention mechanism, we infer and quantify variable importance. Extensive experiments using real datasets with Granger-causality test and the synthetic dataset with ground truth demonstrate the prediction performance and interpretability of multi-variable LSTM in comparison to a variety of baselines. It exhibits the prospect of multi-variable LSTM as an end-to-end framework for both forecasting and knowledge discovery.

The ETSI Experiential Networked Intelligence Industry Specification Group (ISG ENI) has announced the release of its first five specifications on Artificial Intelligence (AI) and machine learning. In adding closed-loop AI mechanisms the group said it's aiming to help operators facilitate their network deployment. The first technical report, ETSI GR ENI 001, specifies a set of use cases to be applied to the fixed network, the mobile network, or both, and defines the expected benefits operators can gain from using an ENI system. These use cases cover infrastructure management, network operations, service orchestration and management, and assurance. The second specification ETSI GS ENI 002 captures the requirements of how intelligence is applied to the network in different scenarios to improve operators' experience of service provision and network operation.

The identical robotic explorers, Spirit and Opportunity, were able to trek up to 109 yards each Martian day. They found evidence for liquid water among many other things, with Opportunity traveling farther than any autonomous vehicle on any world: over 45 km (28 miles) over more than 5000 days. In 2004, NASA launched two exploration vehicles to the red planet: the Spirit and Opportunity rovers. These two Mars Exploration Rovers were originally designed for 90-day missions to image, explore, and investigate the Martian surface. Yet these twin solar-powered rovers far exceeded their design lifetimes.

Recently, a variety of approaches has been enriching the field of Remote Sensing (RS) image processing and analysis. Unfortunately, existing methods remain limited faced to the rich spatio-spectral content of today's large datasets. It would seem intriguing to resort to Deep Learning (DL) based approaches at this stage with regards to their ability to offer accurate semantic interpretation of the data. However, the specificity introduced by the coexistence of spectral and spatial content in the RS datasets widens the scope of the challenges presented to adapt DL methods to these contexts. Therefore, the aim of this paper is firstly to explore the performance of DL architectures for the RS hyperspectral dataset classification and secondly to introduce a new three-dimensional DL approach that enables a joint spectral and spatial information process. A set of three-dimensional schemes is proposed and evaluated. Experimental results based on well knownhyperspectral datasets demonstrate that the proposed method is able to achieve a better classification rate than state of the art methods with lower computational costs.

In this episode of Robots in Depth, Per Sjöborg speaks with Andrew Graham about snake arm robots that can get into impossible locations and do things no other system can. Andrew tells the story about starting OC Robotics as a way to ground his robotics development efforts in a customer need. He felt that making something useful gave a great direction to his projects. We also hear about some of the unique properties of snake arm robots: – They can fit in any space that the tip of the robot can get through – They can operate in very tight locations as they are flexible all along and therefore do not sweep large areas to move – They are easy to seal up so that they don't interact with the environment they operate in – They are set up in two parts where the part exposed to the environment and to risk is the cheaper part Andrew then shares some interesting insights from the many projects he has worked on, from fish processing and suit making to bomb disposal and servicing of nuclear power plants. This interview was recorded in 2015.

The global shipping industry has changed more in the past few years than the previous half of a decade. Artificial intelligence is one of the biggest factors that is spearheading the evolution of this timeless industry. Mike Konstantinidis, The CEO of METIS Cybertechnology provided an especially insightful critique of the impact AI has had on the industry. Konstantinidis points out that the shipping industry was reluctant to invest in new communication technologies during the late 1990s and early 21st century. Artificial intelligence has made it easier for these companies to seamlessly integrate new shipping logistics and communication technology into their business models.

Wandering the halls of CES Asia it's easy to spot the automotive companies, but sometimes you have to look at the logos instead of looking for actual vehicles on display. The booths here at the show in Shanghai, China are full of global and domestic brands showing off everything from self-driving vehicles to futuristic concepts to useful doo-dads for today's cars. The focus of the automakers here at @CESAsia is obviously not on the cars themselves, but on mobility. You hear this a lot, but to see the @Honda booth with no actual cars in it really drives that home. Just because Honda didn't have any actual vehicles on display is not to say that every company wanted to promote mobility ideas over cars.