Using Machine Learning to Drive Retention


Halfbrick Studios is a professional game development studio based in Brisbane, Australia. Founded in 2001, Halfbrick has developed many popular games, including Fruit Ninja, Jetpack Joyride, and Dan the Man. When Halfbrick first learned about Firebase Predictions, they were excited about targeting users based on predicted behavior, rather than historic. Re-engagement is tough, so intervening before a user churned - based on predictions instead of ad hoc heuristics - seemed like a strong strategy. They had been trying to create their own churn prediction models, but like many companies, didn't have the time or resources to properly devote to the problem.

We don't see AI opportunity


If a picture tells a thousand words, these are the two jostling foremost in a patient's mind when a radiologist scans their body for a better image of that suspicious lump or mass. But there is so much more a picture can tell us about cancer, particularly if we consider the possibilities of artificial intelligence. In 2017, US scientists announced they had developed an algorithm, or a computerised tool, to identify skin cancers through analysis of photographs. The algorithm scans a photo of a patch of skin to look for common forms of skin cancer, performing on par with board-certified dermatologists in identifying malignant melanomas (the third most common cancer in Australia) and keratinocyte carcinoma. This technology might enable skin cancer detection in country clinics and suburban GPs' offices at the highest accuracy available.

AI-Powered Gun Detection Is Coming to Mosques Worldwide Following Christchurch Shootings


In March, a gunman walked into two mosques in Christchurch, New Zealand, opened fire, and killed dozens of worshippers. According to a police official, the suspected gunman was arrested 36 minutes after police were called to the scene. Now, a tech company believes its smart security cameras can prevent attacks like the tragedy in Christchurch, and says it plans to install its AI-powered systems in mosques around the world. Athena Security, the tech company behind the security system, and Al-Ameri International Trading announced the Keep Mosques Safe initiative last week. Al-Ameri International Trading, along with several Islamic non-profit groups, will fund the Keep Mosques Safe effort.

Tesla to launch Model 3 in the UK within a week


Tesla's Model 3 will launch in the UK on May 1 or 2, CEO Elon Musk tweeted on Thursday. Launches in Japan, Australia, New Zealand, and Hong Kong will follow "shortly thereafter," Musk said. SEE ALSO: Tesla's new video shows a Model 3 driving itself like it's no big deal Musk later clarified that the UK order page will go live either on May 1 or May 2. The company will delay the $1,000 Full Self-Driving (FSD) price hike until May 10 to accommodate those who were unable to order in time (previously, the price increase was scheduled for May 1). On Friday, Musk also added that he's hoping to cover "all of Eastern Europe" in 2019. Tesla Model 3 was officially unveiled in 2016, but first units were delivered in the U.S. in the second half of 2017.

PAN: Path Integral Based Convolution for Deep Graph Neural Networks

arXiv.org Machine Learning

Convolution operations designed for graph-structured data usually utilize the graph Laplacian, which can be seen as message passing between the adjacent neighbors through a generic random walk. In this paper, we propose PAN, a new graph convolution framework that involves every path linking the message sender and receiver with learnable weights depending on the path length, which corresponds to the maximal entropy random walk. PAN generalizes the graph Laplacian to a new transition matrix we call \emph{maximal entropy transition} (MET) matrix derived from a path integral formalism. Most previous graph convolutional network architectures can be adapted to our framework, and many variations and derivatives based on the path integral idea can be developed. Experimental results show that the path integral based graph neural networks have great learnability and fast convergence rate, and achieve state-of-the-art performance on benchmark tasks.

How Downer is using sensors to predict Sydney Trains maintenance


Australian giant Downer has a 30-year contract with the New South Wales government to manage and maintain its fleet of 78 Waratah trains that operate in the greater Sydney metro area. With 2041 not approaching any time soon, the company recognised a perfect opportunity to maximise technology to make the most of its data and plan for proactive, rather than reactive, maintenance of Sydney's trains. In December 2016, the NSW government ordered 24 Waratah Series 2 trains under its Sydney Growth Trains Project and in February 2019, announced the decision to order 17 more trains. The new trains are touted as providing passengers with improved safety and comfort, fitted with air-con, more CCTV cameras, and improved accessibility. Downer general manager of Digital Technology and Innovation Mike Ayling said his company saw this as the perfect opportunity to leverage additional sensor data from the fleet.

Chorus and partners underestimated migrant worker risk in UFB rollout


While the subcontracting model used for New Zealand's Ultra-Fast Broadband (UFB) network was appropriate to meet the uptick of fibre deployment, as was the use of migrant workers. A review has found that Chorus, Visionstream, and UCG did not manage well or understand how this model became vulnerable to such a risk. "There is evidence that the'UFB Connect' part of the UFB work programme is where the model is exposed to breaches of labour standards and migrant exploitation," the review by MartinJenkins said. "These problems relate to services delivered by two of the service companies, Visionstream and UCG, through a range of subcontracted delivery partners." In October, the Labour Inspectorate arm of Employment New Zealand announced it had completed 75 visits alongside Immigration New Zealand and Inland Revenue in June of 2018 and identified 73 subcontractors in Auckland in breach of minimum employment standards.

Wing Officially Launches Australian Drone Delivery Service

IEEE Spectrum Robotics Channel

Alphabet's subsidiary Wing announced this week that it has officially launched a commercial drone delivery service "to a limited set of eligible homes in the suburbs of Crace, Palmerston and Franklin," which are just north of Canberra, in Australia. Wing's drones are able to drop a variety of small products, including coffee, food, and pharmacy items, shuttling them from local stores to customers' backyards within minutes. We've been skeptical about whether this kind of drone delivery makes sense for a long, long time, and while this is certainly a major milestone for Wing, I'm still not totally convinced that the use-cases that Wing is pushing here are going to be sustainable long term. I've still got a bunch of questions about these things. For example, does the drone have any kind of in-flight sense and avoid?

Google's drone delivery service just got approved for public use in Australia


Drone deliveries have been the subject of many a flashy promo video over the years, but until now, they haven't been available for everyone to use whenever they want. That's still the case in most of the world, but one part of Australia just won the ability to get things delivered through the air. Limited drone deliveries courtesy of Wing are now available in Australia's capital city of Canberra, the drone service announced on Monday. Wing is part of Alphabet, making it one of Google's corporate siblings. At first, Wing drone deliveries will only be available in three suburbs: Palmerston, Franklin and Crace.