Hamiltonian Monte Carlo is typically based on the assumption of an underlying canonical symplectic structure. Numerical integrators designed for the canonical structure are incompatible with motion generated by non-canonical dynamics. These non-canonical dynamics, motivated by examples in physics and symplectic geometry, correspond to techniques such as preconditioning which are routinely used to improve algorithmic performance. Indeed, recently, a special case of non-canonical structure, magnetic Hamiltonian Monte Carlo, was demonstrated to provide advantageous sampling properties. We present a framework for Hamiltonian Monte Carlo using non-canonical symplectic structures. Our experimental results demonstrate sampling advantages associated to Hamiltonian Monte Carlo with non-canonical structure. To summarize our contributions: (i) we develop non-canonical HMC from foundations in symplectic geomtry; (ii) we construct an HMC procedure using implicit integration that satisfies the detailed balance; (iii) we propose to accelerate the sampling using an {\em approximate} explicit methodology; (iv) we study two novel, randomly-generated non-canonical structures: magnetic momentum and the coupled magnet structure, with implicit and explicit integration.

National Basketball Association (NBA) players are highly motivated and skilled experts that solve complex decision making problems at every time point during a game. As a step towards understanding how players make their decisions, we focus on their movement trajectories during games. We propose a method that captures the multi-modal behavior of players, where they might consider multiple trajectories and select the most advantageous one. The method is built on an LSTM-based architecture predicting multiple trajectories and their probabilities, trained by a multi-modal loss function that updates the best trajectories. Experiments on large, fine-grained NBA tracking data show that the proposed method outperforms the state-of-the-art. In addition, the results indicate that the approach generates more realistic trajectories and that it can learn individual playing styles of specific players.

Most existing metric learning methods focus on learning a similarity or distance measure relying on similar and dissimilar relations between sample pairs. However, pairs of samples cannot be simply identified as similar or dissimilar in many real-world applications, e.g., multi-label learning, label distribution learning. To this end, relation alignment metric learning (RAML) framework is proposed to handle the metric learning problem in those scenarios. But RAML framework uses SVR solvers for optimization. It can't learn positive semidefinite distance metric which is necessary in metric learning. In this paper, we propose two methds to overcame the weakness. Further, We carry out several experiments on the single-label classification, multi-label classification, label distribution learning to demonstrate the new methods achieves favorable performance against RAML framework.

Artificial Intelligence (AI) is helping to improve our society, enhance Australia's wellbeing, improve environmental sustainability and create a more equitable, inclusive and fair society. But as we work to reshape government delivery with AI, are we asking the right questions? The role of AI, including policy implications and the nature of industry in society, is being discussed today in a live-stream event co-hosted by the Institute of Public Administration Australia (IPAA) and the Australian Council of Learned Academies (ACOLA). ACOLA CEO Ryan Winn said the event will feature a keynote presentation by Australia's Chief Scientist, Dr Alan Finkel AO and a panel discussion with ACOLA's AI Expert Group and key Government officials leading AI implementation. "The event will give rise to further discussion on the future opportunities and challenges of AI in industry and Government operations and service delivery, and what implications this will have on society for 2030," Mr Winn said.

As organizations gain more experience deploying machine learning (ML) and artificial intelligence (AI) across different parts of the business, they're discovering new and interesting ways to use the technology. Typical use cases include established applications such as personalization, fraud detection, and speech recognition. But there's much more to explore. "The cloud enables extremely low-cost compute and storage, which opens up opportunities for more modeling," says Sri Elaprolu, senior leader, Amazon Machine Learning Solutions Lab. "There's lots of innovation yet to happen. We are barely scratching the surface."

Mining is a traditionally analogue business. After all, the industry's symbol worldwide is a hammer and pick. Yet, despite the sector's antiquated reputation, some major mining companies are taking a progressive stance and proving digitisation and automation can achieve much better operational outcomes. Known as Mine 4.0, the industry is seeing digital transformation creep into everything from trucks, drills and trains to back-office processes, such as procurement and supply chain logistics. Miners have very little control over the revenue side of their business, as the global commodities crash of 2014 to 2015, when prices plunged by more than 30 per cent, and indeed the coronavirus epidemic demonstrate.

Men fed up with the old adage that they are unable to multitask can take solace from a recent piece of research which found the ability can be improved with practise. Scientists found people improve thanks to improved information transfer between a round structure within the brain called the putamen and the organ's outer regions. Australian neuroscientists compared the brain activity of 100 healthy adults before and after a week of practising two tasks at once. MRI scans showed improved information transfer between the putamen and the two outer regions, known as the IPS and the pre-SMA. 'Humans show striking limitations in information processing when multitasking, yet can modify these limits with practice,' said the study authors from the University of Queensland, Australia.

The taxation of multi-national companies is a complex field, since it is influenced by the legislation of several states. Laws in different states may have unforeseen interaction effects, which can be exploited by allowing multinational companies to minimize taxes, a concept known as tax planning. In this paper, we present a knowledge graph of multinational companies and their relationships, comprising almost 1.5M business entities. We show that commonly known tax planning strategies can be formulated as subgraph queries to that graph, which allows for identifying companies using certain strategies. Moreover, we demonstrate that we can identify anomalies in the graph which hint at potential tax planning strategies, and we show how to enhance those analyses by incorporating information from Wikidata using federated queries.

Short-term forecasting is an important tool in understanding environmental processes. In this paper, we incorporate machine learning algorithms into a conditional distribution estimator for the purposes of forecasting tropical cyclone intensity. Many machine learning techniques give a single-point prediction of the conditional distribution of the target variable, which does not give a full accounting of the prediction variability. Conditional distribution estimation can provide extra insight on predicted response behavior, which could influence decision-making and policy. We propose a technique that simultaneously estimates the entire conditional distribution and flexibly allows for machine learning techniques to be incorporated. A smooth model is fit over both the target variable and covariates, and a logistic transformation is applied on the model output layer to produce an expression of the conditional density function. We provide two examples of machine learning models that can be used, polynomial regression and deep learning models. To achieve computational efficiency we propose a case-control sampling approximation to the conditional distribution. A simulation study for four different data distributions highlights the effectiveness of our method compared to other machine learning-based conditional distribution estimation techniques. We then demonstrate the utility of our approach for forecasting purposes using tropical cyclone data from the Atlantic Seaboard. This paper gives a proof of concept for the promise of our method, further computational developments can fully unlock its insights in more complex forecasting and other applications.

Generating diverse and relevant questions over text is a task with widespread applications. We argue that commonly-used evaluation metrics such as BLEU and METEOR are not suitable for this task due to the inherent diversity of reference questions, and propose a scheme for extending conventional metrics to reflect diversity. We furthermore propose a variational encoder-decoder model for this task. We show through automatic and human evaluation that our variational model improves diversity without loss of quality, and demonstrate how our evaluation scheme reflects this improvement.