We propose a new variational Bayes method for estimating high-dimensional copulas with discrete, or discrete and continuous, margins. The method is based on a variational approximation to a tractable augmented posterior, and is substantially faster than previous likelihood-based approaches. We use it to estimate drawable vine copulas for univariate and multivariate Markov ordinal and mixed time series. These have dimension $rT$, where $T$ is the number of observations and $r$ is the number of series, and are difficult to estimate using previous methods. The vine pair-copulas are carefully selected to allow for heteroskedasticity, which is a common feature of ordinal time series data. When combined with flexible margins, the resulting time series models also allow for other common features of ordinal data, such as zero inflation, multiple modes and under- or over-dispersion. Using data on homicides in New South Wales, and also U.S bankruptcies, we illustrate both the flexibility of the time series copula models, and the efficacy of the variational Bayes estimator for copulas of up to 792 dimensions and 60 parameters. This far exceeds the size and complexity of copula models for discrete data that can be estimated using previous methods.

Rob Pennicott is from Pennicott Wilderness Journeys in Tasmania and Kayla Itsines and Toby Pearce set up and run the global fitness brand Sweat. The founders of both these businesses were inspirational, brave, moving and above all, completely energising. Their stories have some similar themes but what stood out in both cases for me is that they are highly creative people. They are passionate about their ideas, they have created something original out of nothing even when they were told "it will never work" or "you're crazy" by the Nay Sayers and they had, and continue to have, the ability to imagine what could be, and turn that imagination into reality. Whilst both endured their fair share of financial challenges in the early stages, it was never money that drove them.

It's been yet another big year of disruption in marketing. From the intricacies of customer-led digital transformation to debates around brand safety and digital advertising viewability and efficiency, modern marketing skillsets and the rise of artificial intelligence, augmented and virtual reality and now voice-based interface design, there's no shortage of big topics that have been in the spotlight this year. To help highlight some of the biggest trends of the year, CMO has pulled together a list of our most-read stories for 2017 to showcase how marketers are working to modernise their approach and what's grabbed their attention. Australia's top marketing leaders are commanding ever-higher levels of authority in companies across the country. And in just three years, it's amazing how far the CMO remit has come.

Brisbane, Australia-based ResApp is planning to re-do its big US trial soon, but in the meantime the smartphone respiratory diagnosis company is continuing to collect data in its native country. The company released data yesterday from a clinical study of more than 1,300 adult patients at Joondalup Health Campus in Perth and Wesley Hospital in Brisbane. While the company's previous studies have focused on a particular condition, this is the first real-world study of patients with a wide variety of diagnoses. Patients presented with a range of respiratory conditions, including some with no condition at all. "Delivering accurate results within an adult intended use population is an excellent step forward, further demonstrating that ResApp's algorithms can be applied effectively in a group of patients with a very broad range of respiratory illnesses," Tony Keating, CEO and managing director of ResApp Health, said in a statement.

NEC Australia, a leading ICT solutions and services company, has entered a strategic partnership with Silicon Valley vision analytics firm, CrowdOptic, to bring next generation security to smart cities. NEC Australia and CrowdOptic are jointly introducing a ground-breaking intelligent live video streaming security system enabled by real-time analysis of footage captured from fixed cameras and mobile camera sensors in body cams, smartphones, and drones. This marks a significant improvement on video surveillance and facial recognition, which today relies predominantly on footage captured from fixed cameras. Live, intelligent video footage combined with efficient transmission of data from mobile camera sensors enhances the impact of the world's most accurate face recognition technology (NEC's Video Face Recognition Technology Ranks First in NIST Testing), NeoFace . Naturally, mobility will play an important role in smart city technology.

This article first appeared in the Autumn 2017 issue of The Record. Fashion retailer City Beach, for example, operates an e- commerce outlet and 62 stores across Australia, adding 300-400 new lines to its 60,000-strong product portfolio each week. Meanwhile, US-based homeware and décor brand Pier 1 Imports has an online store, boutiques in Mexico and 1,000 physical stores across North America. But how do these retailers know which products will sell? And how do they choose the optimum product assortment and inventory level to ensure that they can always meet customer demand?

Companies in the Asia-Pacific region are ahead in the adoption of disruptive technologies such as Internet of Things, artificial intelligence, says a recent global survey of chief information officers (CIOs)by by Gartner, Inc. The survey covers CIOs worldwide, including 537 across 17 countries in Asia/Pacific (113 of those in Australia and New Zealand) and represents approximately $3.4 trillion in revenue/public sector budgets and $49 billion in IT spending. According to the survey, about 43 per cent of surveyed CIOs in Asia-Pacific region have said that either they have deployed or have plans for deployment of IoT technologies, compared to 37 per cent globally. Some 37 per cent have deployed AI compared to 25 per cent globally. In the region, 28 per cent CIOs have made investments in conversational interfaces, 20 per cent in virtual reality (VR) and augmented reality, while 13 per cent have adopted blockchain or distributed ledger technology.

As travelers take to the beaches in Australia in the summer, they'll now have the benefit of drones to warn them if a shark is close to shore. A link has been posted to your Facebook feed. As travelers take to the beaches in Australia in the summer, they'll now have the benefit of drones to warn them if a shark is close to shore.

A classification algorithm, called the Linear Centralization Classifier (LCC), is introduced. The algorithm seeks to find a transformation that best maps instances from the feature space to a space where they concentrate towards the center of their own classes, while maximimizing the distance between class centers. We formulate the classifier as a quadratic program with quadratic constraints. We then simplify this formulation to a linear program that can be solved effectively using a linear programming solver (e.g., simplex-dual). We extend the formulation for LCC to enable the use of kernel functions for non-linear classification applications. We compare our method with two standard classification methods (support vector machine and linear discriminant analysis) and four state-of-the-art classification methods when they are applied to eight standard classification datasets. Our experimental results show that LCC is able to classify instances more accurately (based on the area under the receiver operating characteristic) in comparison to other tested methods on the chosen datasets. We also report the results for LCC with a particular kernel to solve for synthetic non-linear classification problems.

Fuelled by successes in Computer Go, Monte Carlo tree search (MCTS) has achieved widespread adoption within the games community. Its links to traditional reinforcement learning (RL) methods have been outlined in the past; however, the use of RL techniques within tree search has not been thoroughly studied yet. In this paper we re-examine in depth this close relation between the two fields; our goal is to improve the cross-awareness between the two communities. We show that a straightforward adaptation of RL semantics within tree search can lead to a wealth of new algorithms, for which the traditional MCTS is only one of the variants. We confirm that planning methods inspired by RL in conjunction with online search demonstrate encouraging results on several classic board games and in arcade video game competitions, where our algorithm recently ranked first. Our study promotes a unified view of learning, planning, and search.