The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner. Here, we coherently propose an approach for embedding entire graphs and show that our feature representations with SVM classifier increase classification accuracy of CNN algorithms and traditional graph kernels. For this we describe a recently discovered graph object, anonymous walk, on which we design task-independent algorithms for learning graph representations in explicit and distributed way. Overall, our work represents a new scalable unsupervised learning of state-of-the-art representations of entire graphs.

Rob Bollard, CIO at IP Australia, the government's intellectual property department, is proud to say that he heads up Australia's first fully digital service delivery agency. In just the space of four years, IP Australia has gone from receiving just 12% of its IP applications online – the rest coming through on paper – to now receiving 99.6% through digital channels. Not only his, but Bollard is overseeing the decommissioning of old systems, a move to the cloud, has implemented agile working, created a DevOps environment that focuses on continuous delivery, ensures systems are designed with the user in mind, and is even deploying AI technologies to improve experiences for employees and citizens. I got the chance to sit down with Bollard at Pega's annual user event in Las Vegas this week, as IP Australia has implemented the Pega platform as its case management system. Our vision is really to become a world-class IP office and to try to support the prosperity of Australians in the system.

A Tesla's autopilot function was engaged in the minutes before a fiery crash that killed its driver in California earlier this year, according to a federal inquiry. In the roughly 20 minutes before the vehicle slammed into a barrier near Mountain View and burst into flames, the car's autopilot feature was in "continuous operation", the National Transportation Safety Board (NTSB) found in its initial investigation. During the critical 60 seconds leading up to the crash, the NTSB reported, the car's driver repeatedly placed his hands on the steering wheel. Tesla crashes into parked police car in Autopilot mode Wall Street blasts Elon Musk's'truly bizarre' Tesla earnings call Tesla faces labour investigation after allegation of injury undercount But six seconds before the accident, evidence suggests the driver had removed his hands from the steering wheel. The vehicle also accelerated in the final three seconds.

Give us your feedback Thank you for your feedback. Parker's first day at work at the law firm Norton Rose Fulbright in Australia involved 1,000 conversations with potential clients. Even the most super-energetic young lawyer would normally manage only a fraction of that but Parker is, of course, a chatbot -- a computer program that simulates human conversation. The new recruit is a prime example of how law firms in Asia-Pacific are experimenting with artificial intelligence to improve efficiency. Chatbots, which use AI to answer simple questions from people wanting to learn more about a subject, are already being adopted in industries ranging from banking to medicine.

A new drone surveillance system can spot when someone in a crowd is acting violently. It uses artificial intelligence and is going to be tested at a university festival in India later this year. The system assesses the way each person in a crowd is standing via two cameras on the drone. To continue reading this premium article, subscribe for unlimited access. Existing subscribers, please log in with your email address to link your account access.

Edwin V. Bonilla School of Computer Science and Engineering University of New South Wales Sydney, Australia We consider multi-task regression models where the observations are assumed to be a linear combination of several latent node functions and weight functions, which are both drawn from Gaussian process priors. Driven by the problem of developing scalable methods for distributed solar power forecasting, we propose coupled priors over groups of (node or weight) processes to estimate a forecast model for solar power production at multiple distributed sites, exploiting spatial dependence between functions. Our results show that our approach provides better quantification of predictive uncertainties than competing benchmarks while maintaining high point-prediction accuracy.

Japanese researchers have developed an astonishing robot with a snake-like body that is capable of fighting fires. The'dragon robot' is capable of wriggling into hard-to-reach gaps between structures and windows several floors up. It therefore can extinguish blazes traditional firefighters might not be able to reach. Researchers from Tohoku University and National Institute of Technology, Hachinohe College presented the robot at the International Conference on Robotics and Automation last month in Brisbane, Australia. The machine, called the DragonFireFighter, has the ability to lift itself off the ground and fly using high pressure jets of water.

As artificial agents proliferate, it is becoming increasingly important to ensure that their interactions with one another are well-behaved. In this paper, we formalize a common-sense notion of when algorithms are well-behaved: an algorithm is safe if it does no harm. Motivated by recent progress in deep learning, we focus on the specific case where agents update their actions according to gradient descent. The paper shows that that gradient descent converges to a Nash equilibrium in safe games. The main contribution is to define strongly-typed agents and show they are guaranteed to interact safely, thereby providing sufficient conditions to guarantee safe interactions. A series of examples show that strong-typing generalizes certain key features of convexity, is closely related to blind source separation, and introduces a new perspective on classical multilinear games based on tensor decomposition.

This Ph.D. thesis deals with the optimization of several renewable energy resources development as well as the improvement of facilities management in oceanic engineering and airports, using computational hybrid methods belonging to AI to this end. Energy is essential to our society in order to ensure a good quality of life. This means that predictions over the characteristics on which renewable energies depend are necessary, in order to know the amount of energy that will be obtained at any time. The second topic tackled in this thesis is related to the basic parameters that influence in different marine activities and airports, whose knowledge is necessary to develop a proper facilities management in these environments. Within this work, a study of the state-of-the-art Machine Learning have been performed to solve the problems associated with the topics above-mentioned, and several contributions have been proposed: One of the pillars of this work is focused on the estimation of the most important parameters in the exploitation of renewable resources. The second contribution of this thesis is related to feature selection problems. The proposed methodologies are applied to multiple problems: the prediction of $H_s$, relevant for marine energy applications and marine activities, the estimation of WPREs, undesirable variations in the electric power produced by a wind farm, the prediction of global solar radiation in areas from Spain and Australia, really important in terms of solar energy, and the prediction of low-visibility events at airports. All of these practical issues are developed with the consequent previous data analysis, normally, in terms of meteorological variables.

We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations of entities from one domain as entities from the other domain. First, we introduce implicit latent variable models, where the prior over hidden representations can be specified flexibly as an implicit distribution. Next, we develop a new variational inference (VI) algorithm for this model based on minimization of the symmetric Kullback-Leibler (KL) divergence between a variational joint and the exact joint distribution. Lastly, we demonstrate that the state-of-the-art cycle-consistent adversarial learning (CYCLEGAN) models can be derived as a special case within our proposed VI framework, thus establishing its connection to approximate Bayesian inference methods.