Many countries are suffering from severe air pollution. Understanding how different air pollutants accumulate and propagate is critical to making relevant public policies. In this paper, we use urban big data (air quality data and meteorological data) to identify the \emph{spatiotemporal (ST) causal pathways} for air pollutants. This problem is challenging because: (1) there are numerous noisy and low-pollution periods in the raw air quality data, which may lead to unreliable causality analysis, (2) for large-scale data in the ST space, the computational complexity of constructing a causal structure is very high, and (3) the \emph{ST causal pathways} are complex due to the interactions of multiple pollutants and the influence of environmental factors. Therefore, we present \emph{p-Causality}, a novel pattern-aided causality analysis approach that combines the strengths of \emph{pattern mining} and \emph{Bayesian learning} to efficiently and faithfully identify the \emph{ST causal pathways}. First, \emph{Pattern mining} helps suppress the noise by capturing frequent evolving patterns (FEPs) of each monitoring sensor, and greatly reduce the complexity by selecting the pattern-matched sensors as "causers". Then, \emph{Bayesian learning} carefully encodes the local and ST causal relations with a Gaussian Bayesian network (GBN)-based graphical model, which also integrates environmental influences to minimize biases in the final results. We evaluate our approach with three real-world data sets containing 982 air quality sensors, in three regions of China from 01-Jun-2013 to 19-Dec-2015. Results show that our approach outperforms the traditional causal structure learning methods in time efficiency, inference accuracy and interpretability.

When artificial intelligence works smoothly, computers are able to spot cats in photographs at lightning-fast speeds. When it goes wrong, they can confuse images of turtles with rifles. Researchers from MIT's computer science and artificial intelligence laboratory have discovered how to trick Google's (goog) software that automatically recognizes objects in images. They created an algorithm that subtly modified a photo of a turtle so that Google's image-recognition software thought it was a rifle. What's especially noteworthy is that when the MIT team created a 3D printout of the turtle, Google's software still thought it was a weapon rather than a reptile.

A new partnership between Rolls-Royce and Google will see ships become smarter and self-learning thanks to advanced machine learning algorithms. It will also bring the company's vision of a fully autonomous ship setting sail by 2020 a step closer to reality. Rolls Royce announced this month that it will use Google's Cloud Machine Learning Engine across a range of applications, designed to both make today's ships safer and more efficient, and to launch the ships of tomorrow. Initially the machine learning engine will be used to further train existing AI algorithms designed to power the image recognition systems of vessels. These identify and track objects that can be encountered while a ship is at sea and classify them according to the hazards they may pose.

The EnhanceNet-PAT algorithm could help with everything from restoring old photos to improving image recognition for self-driving cars. Anyone who has ever worked with image files knows that, unlike the fictional world of shows like CSI, there's no easy way to take a low-resolution image and magically transform it into a high-resolution picture using some fancy "enhance" tool. Fortunately, some brilliant computer scientists at the Max Planck Institute for Intelligent Systems in Germany are working on the problem -- and they've come up with a pretty nifty algorithm to address it. What they have developed is a tool called EnhanceNet-PAT, which uses artificial intelligence to create high-definition versions of low-res images. While the solution is not a miracle fix, it does produce a noticeably better result than previous attempts, thanks to some smart machine-learning algorithms.

But it does seem that way. A newly viral post is encouraging people to find out the "folder", and look at what is contained in there. And while some of the reports are true, they aren't all – or as intimate – they seem. The tweet – since reposted more than 10,000 times – instructs all women to go and search "brassiere" in their pictures. Many reported that it revealed some of their most intimate pictures, including some of them entirely naked or even having sex.

Can a computer automatically detect pictures of shirts, pants, dresses, and sneakers? It turns out that accurately classifying images of fashion items is surprisingly straight-forward to do, given quality training data to start from. Supervised learning, in particular for classification, is a popular topic amongst artificial intelligence and machine learning enthusiasts. It's common for developers to utilize a well known and easy to process dataset for their first attempts at using supervised learning. The MNIST dataset is an example of such a source, providing thousands of examples of handwritten digits that can be used for supervised learning with your machine learning algorithms. I've previously written about classifying handwritten digits with the MNIST data-set, achieving accuracies of 99% on the training set and 97% on the test set. Data sets such as these are a convenient way to hone your skills and machine learning model development with a tried and trusted data source. It's important to keep in mind that a good data set has several features in common.

Traditionally, template-matching algorithms have been used for things like digital image processing and visual pattern recognition. One simple example of this deals with taking a (typically very small) two-dimensional filter and sliding it across an image in order to detect low-level patterns of black-and-white pixels. Pattern recognition through template-matching is currently restricted in that it is only useful when dealing with vector spaces. However, problems of high complexity tend to deal with conceptually abstract relations and not with patterns dependent on space-time. In the following framework, I propose a feasible solution for extending template-matching methods to topological space, like graphs and networks.

Data Science is one of the most-sought after professions today. Universities across the world are offering courses in this discipline which stands testimony to this emerging profession. There are a very few professionals with the required skill and the demand for data scientists is racing ahead. The tutorial wil give a brief understanding about Data Science. 'Implementing Machine Learning Algorithms on Larger Data Sets with Apache Mahout' have been widely covered in our course'Data Science'.

This tutorial shows how to build an image recognition service in Go using pre-trained TensorFlow Inception-V3 model. The service will run inside a Docker container, use TensorFlow Go package to process images and return labels that best describe them. Full source code is available on GitHub. Inside project's root directory create docker-compose.yaml It uses official TensorFlow Docker image as its base image.

Artificial intelligence has conquered games and image recognition, but will it master investing? The short answer is yes, but how soon and how complete? Machine learning methods have had impressive recent successes. These include defeating humans at chess, Jeopardy, poker and Go, as well as providing superior image and speech recognition. Developers strive to create tools that automate decision making and that can mimic or exceed human performance for specific tasks.