At 6:40 in the morning, a klaxon horn sounds three times. "Gas!" a man in a hard hat and fluorescent vest yells out. There's a hissing noise, and the helium starts flowing. From the tanks stacked like cordwood on a nearby truck, the gas moves through a series of hoses until it's 55 feet up, then through a copper pipe and into the top of a plastic tube that hangs down to the ground, like a shed snake skin held up for inspection. It's a Wednesday in late June in Winnemucca, a solitary mining town in northern Nevada that has avoided oblivion by straddling the I-80 freeway. Along with two Basque restaurants, the Buckaroo Hall of Fame, and a giant W carved into the side of a hill, Winnemucca is the test site for Project Loon, a grandiose scheme launched in 2011 to bring the internet to huge swaths of the planet where sparse population and challenging geography make the usual networks of cell towers a nonstarter.

LONDON – Britain's data regulator will fine Facebook half a million pounds ($660,000) for failing to protect users' data, in an inquiry into whether personal information had been misused by campaigns on both sides of Britain's 2016 EU referendum. An investigation by the Information Commissioner's Office (ICO) has focused on the social media giant since earlier this year, when evidence emerged that an app had been used to harvest the data of tens of millions of Facebook users worldwide. In a progress report early Wednesday the watchdog said it plans to issue Facebook with the maximum fine available to it for breaches of the Data Protection Act. "The ICO's investigation concluded that Facebook contravened the law by failing to safeguard people's information," it said, adding that the company had "failed to be transparent about how people's data was harvested by others." Facebook has admitted that up to 87 million users may have had their data hijacked by British consultancy firm Cambridge Analytica, which was working for U.S. President Donald Trump's 2016 campaign.

The API provides pre-trained object detection models that have been trained on the COCO dataset. COCO dataset is a set of 90 commonly found objects. See image below of objects that are part of COCO dataset. In this case we care about classes -- persons and soccer ball which are both part of COCO dataset. The API also has a big set of models it supports. See table below for reference. The models have a trade off between speed and accuracy. Since I was interested in real time analysis, I chose SSDLite mobilenet v2. Once we identify the players using the object detection API, to predict which team they are in we can use OpenCV which is powerful library for image processing.

The ability to learn from incrementally arriving data is essential for any life-long learning system. However, standard deep neural networks forget the knowledge about the old tasks, a phenomenon called catastrophic forgetting, when trained on incrementally arriving data. We discuss the biases in current Generative Adversarial Networks (GAN) based approaches that learn the classifier by knowledge distillation from previously trained classifiers. These biases cause the trained classifier to perform poorly. We propose an approach to remove these biases by distilling knowledge from the classifier of AC-GAN. Experiments on MNIST and CIFAR10 show that this method is comparable to current state of the art rehearsal based approaches. The code for this paper is available at https://bit.ly/incremental-learning

Wagner's modularity inducing problem domain is a key contribution to the study of the evolution of modularity, including both evolutionary theory and evolutionary computation. We study its behavior under classical genetic algorithms. Unlike what we seem to observe in nature, the emergence of modularity is highly conditional and dependent, for example, on the eagerness of search. In nature, modular solutions generally dominate populations, whereas in this domain, modularity, when it emerges, is a relatively rare variant. Emergence of modularity depends heavily on random fluctuations in the fitness function; with a randomly varied but unchanging fitness function, modularity evolved far more rarely. Interestingly, high-fitness non-modular solutions could frequently be converted into even-higher-fitness modular solutions by manually removing all inter-module edges. Despite careful exploration, we do not yet have a full explanation of why the genetic algorithm was unable to find these better solutions.

Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are one of the most prominent tools for learning complicated distributions. However, problems such as mode collapse and catastrophic forgetting, prevent GAN from learning the target distribution. These problems are usually studied independently from each other. In this paper, we show that both problems are present in GAN and their combined effect makes the training of GAN unstable. We also show that methods such as gradient penalties and momentum based optimizers can improve the stability of GAN by effectively preventing these problems from happening. Finally, we study a mechanism for mode collapse to occur and propagate in feedforward neural networks.

Two start-ups leading the race to build the first self-flying taxis are using money from the US military. Last year, Kitty Hawk and Joby Aviation received a total of nearly $2m from the Defense Innovation Unit Experimental (DIUx), a Pentagon organization founded to help America's military make faster use of emerging technologies. Neither company, nor the DIUx, disclosed the funding at the time. The website for Cora, Kitty Hawk's experimental air taxi, emphasizes its role in solving urban transportation challenges: "Cora is about the time you could save soaring over traffic. The people you could visit.

On May 27, a deluge dumped more than 6 inches of rain in less than three hours on Ellicott City, Maryland, killing one person and transforming Main Street into what looked like Class V river rapids, with cars tossed about like rubber ducks. The National Weather Service put the probability of such a storm at once in 1,000 years. Yet, "it's the second time it's happened in the last three years," says Jeff Allenby, director of conservation technology for Chesapeake Conservancy, an environmental group. Floods are nothing new in Ellicott City, located where two tributaries join the Patapsco River. But Allenby says the floods are getting worse, as development covers what used to be the "natural sponge of a forest" with paved surfaces, rooftops, and lawns.

Have you put a bet on the FIFA World Cup? If yes, the chances are you've made a pretty educated guess, right? You know which team has the strongest players or most favourable odds. Or maybe you've put some cash on your country's team, (which normally I'd avoid England, but given their recent performance, I could be wrong to!) Either way, you might be best casting your bets in line with San Francisco based Unanimous AI. They use a technology called Swarm AI – algorithms modelled on swarms in nature that amplifies human intelligence.

The drone makes a conspicuous racket as it lifts off on a mission to capture images of the reservoir below. The sight and sound of this strange device stirs interest among locals as they make their way to and from the town of Kasungu in central Malawi. It takes a matter of minutes for a small crowd to form. A few yards away, Patrick Kalonde is wading through grass and mud. Patrick, an intern at Unicef working on humanitarian uses of drones, is carrying a plastic container and a ladle and is looking for mosquito larvae. The contrast between high-tech drones and low-tech "bucket-and-spade" science, metres apart, could not be starker – yet both are equally important to the success of our new project to map where mosquitoes breed. Kasungu, a small town at the base of the picturesque Kasungu Mountain, is the centre of Africa's first humanitarian drone testing corridor. Set up by Unicef in 2017 with support from the Malawi government, the corridor is an 80km-wide area for flying and testing drones to help the local people. Keen to dispel the reputation that drones are only useful for destruction, the Unicef corridor promotes "drones for good".