We propose a new STAcked and Reconstructed Graph Convolutional Networks (STAR-GCN) architecture to learn node representations for boosting the performance in recommender systems, especially in the cold start scenario. STAR-GCN employs a stack of GCN encoder-decoders combined with intermediate supervision to improve the final prediction performance. Unlike the graph convolutional matrix completion model with one-hot encoding node inputs, our STAR-GCN learns low-dimensional user and item latent factors as the input to restrain the model space complexity. Moreover, our STAR-GCN can produce node embeddings for new nodes by reconstructing masked input node embeddings, which essentially tackles the cold start problem. Furthermore, we discover a label leakage issue when training GCN-based models for link prediction tasks and propose a training strategy to avoid the issue. Empirical results on multiple rating prediction benchmarks demonstrate our model achieves state-of-the-art performance in four out of five real-world datasets and significant improvements in predicting ratings in the cold start scenario. The code implementation is available in https://github.com/jennyzhang0215/STAR-GCN.

Why do deep neural networks generalize with a very high dimensional parameter space? We took an information theoretic approach. We find that the dimensionality of the parameter space can be studied by singular semi-Riemannian geometry and is upper-bounded by the sample size. We adapt Fisher information to this singular neuromanifold. We use random matrix theory to derive a minimum description length of a deep learning model, where the spectrum of the Fisher information matrix plays a key role to improve generalisation.

Vehicle speed monitoring and management of highways is the critical problem of the road in this modern age of growing technology and population. A poor management results in frequent traffic jam, traffic rules violation and fatal road accidents. Using traditional techniques of RADAR, LIDAR and LASAR to address this problem is time-consuming, expensive and tedious. This paper presents an efficient framework to produce a simple, cost efficient and intelligent system for vehicle speed monitoring. The proposed method uses an HD (High Definition) camera mounted on the road side either on a pole or on a traffic signal for recording video frames. On the basis of these frames, a vehicle can be tracked by using radius growing method, and its speed can be calculated by calculating vehicle mask and its displacement in consecutive frames. The method uses pattern recognition, digital image processing and mathematical techniques for vehicle detection, tracking and speed calculation. The validity of the proposed model is proved by testing it on different highways.

Quivering and hesitant, like a spoon-wielding toddler trying to eat soup without spilling it, the world's first raspberry-picking robot is attempting to harvest one of the fruits. After sizing it up for an age, the robot plucks the fruit with its gripping arm and gingerly deposits it into a waiting punnet. The whole process takes about a minute for a single berry. It seems like heavy going for a robot that cost £700,000 to develop but, if all goes to plan, this is the future of fruit-picking. Each robot will be able to pick more than 25,000 raspberries a day, outpacing human workers who manage about 15,000 in an eight-hour shift, according to Fieldwork Robotics, a spinout from the University of Plymouth.

A research report on "Global Automotive Artificial Intelligence (AI) Market 2019 Industry Research Report" is being published by researchunt.com. This is a key document as far as the clients and industries are concerned to not only understand the Global competitive market status that exists currently but also what future holds for it in the upcoming period, i.e., between 2018 and 2025. It has taken the previous market status of 2013 – 2018 to project the future status. The report has categorized in terms of region, type, key industries, and application. Global Automotive Artificial Intelligence (AI) revenue was xx.xx Million USD in 2013, grew to xx.xx Million USD in 2017, and will reach xx.xx Million USD in 2023, with a CAGR of x.x% during 2018-2023.

WHEN manufacturers think of artificial intelligence (AI), they think of its ability to produce insights from data. Most manufacturers are keen on using AI to analyze demand and factor in lags in the supply chain to optimize operations, but forget the heavy equipment they're using. According to a new whitepaper, McKinsey argues that companies with heavy assets can reap great dividends if their operators start using AI to review their workflows and make necessary alterations. "AI can deliver improvements without capital-intensive equipment upgrades and thus produce attractive returns quickly," it says. The consulting giant finds that despite the advances in technology, operators of heavy machinery still rely on judgment and intuition to manually monitor signals and adjust settings, troubleshoot and run tests, and perform other tasks that strain the limits of their human capacity.

Norwegian chemical company Yara International has teamed up with tech giant IBM to transform the future of farming. The two companies together endeavour to build the "world's leading" digital farming platform which, they say, will provide holistic digital services and instant agronomic advice. Yara and IBM Services will jointly innovate and commercialise digital agricultural solutions that will help increase global food production. The collaboration will draw on Yara's agronomic knowledge – backed by more than 800 agronomists and a century of experience – and IBM's digital platforms, services and expertise in AI and data analytics. "Our collaboration centres around a common goal to make a real difference in agriculture," said Terje Knutsen, EVP Sales and Marketing in Yara.

It has recently been published that Facebook's development center in Israel is increasing its artificial intelligence (AI) capabilities. The company has established a team, called Data.AI, for developing AI tools that are intended to help build and improve software infrastructure and systems for data research on facebook. According to Facebook, these tools are intended to improve and optimize the work that Facebook's international engineers and programmers handle. "If up until now most of Facebook's efforts in the AI field has focused on advancing and improving the user's experience, then now another dimension is being added by the Israeli team – the development of AI based capabilities towards the improvement of infrastructure and the capabilities of the internal interfaces of the company," Facebook mentions.

The future of car traffic is self-propelled or at least much more automated than before. Keeping an eye on the many variables and possible situations requires exactly the qualities that a well-designed AI system brings with it. In this way, traffic runs more smoothly and, above all, more safely for all concerned. This is not even about your own vehicle. In China, for example, artificial intelligence is used to dynamically and automatically control traffic light circuits so that ambulances, police or fire brigades can arrive at the scene more quickly and provide assistance.

Are you sure you want to view these Tweets? Not to the point where it's clearly insane, but be persistent." By 2020, the number of passwords used by humans and machines worldwide is estimated to grow to 300 BILLION. Join @KirkDBorne and I for my 2nd episode as host of the @SAP #TechUnknown podcast!We discussed The Hubble Telescope, #AI, #DataAnalytics, #DigitalTransformation, Breaking down silos & more. What Are The Most Significant #AI Advances We Will See In The Near Future?