Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks such as WMT. However, there still exist significant issues such as robustness, domain generalization, etc. In this paper, we study NMT models from the perspective of compositional generalization by building a benchmark dataset, CoGnition, consisting of 216k clean and consistent sentence pairs. We quantitatively analyze effects of various factors using compound translation error rate, then demonstrate that the NMT model fails badly on compositional generalization, although it performs remarkably well under traditional metrics.

This work presents an analysis of the Duckworth-Lewis-Stern (DLS) method for One Day International (ODI) cricket matches. The accuracy of the DLS method is compared against various supervised learning algorithms for result prediction. The result of a cricket match is predicted during the second inning. The paper also optimized DLS resource table which is used in the Duckworth-Lewis (D/L) formula to increase its predictive power. Finally, an Unpredictability Index is developed that ranks different cricket playing nations according to how unpredictable they are while playing an ODI match.

Sophisticated trajectory prediction models that effectively mimic team dynamics have many potential uses for sports coaches, broadcasters and spectators. However, through experiments on soccer data we found that it can be surprisingly challenging to train a deep learning model for player trajectory prediction which outperforms linear extrapolation on average distance between predicted and true future trajectories. We propose and test a novel method for improving training by predicting a sparse trajectory and interpolating using constant acceleration, which improves performance for several models. This interpolation can also be used on models that aren't trained with sparse outputs, and we find that this consistently improves performance for all tested models. Additionally, we find that the accuracy of predicted trajectories for a subset of players can be improved by conditioning on the full trajectories of the other players, and that this is further improved when combined with sparse predictions. We also propose a novel architecture using graph networks and multi-head attention (GraN-MA) which achieves better performance than other tested state-of-the-art models on our dataset and is trivially adapted for both sparse trajectories and full-trajectory conditioned trajectory prediction.

Bayesian phylogenetic inference is often conducted via local or sequential search over topologies and branch lengths using algorithms such as random-walk Markov chain Monte Carlo (MCMC) or Combinatorial Sequential Monte Carlo (CSMC). However, when MCMC is used for evolutionary parameter learning, convergence requires long runs with inefficient exploration of the state space. We introduce Variational Combinatorial Sequential Monte Carlo (VCSMC), a powerful framework that establishes variational sequential search to learn distributions over intricate combinatorial structures. We then develop nested CSMC, an efficient proposal distribution for CSMC and prove that nested CSMC is an exact approximation to the (intractable) locally optimal proposal. We use nested CSMC to define a second objective, VNCSMC which yields tighter lower bounds than VCSMC. We show that VCSMC and VNCSMC are computationally efficient and explore higher probability spaces than existing methods on a range of tasks.

Time series classification (TSC) aims to predict the class label of a given time series, which is critical to a rich set of application areas such as economics and medicine. State-of-the-art TSC methods have mostly focused on classification accuracy and efficiency, without considering the interpretability of their classifications, which is an important property required by modern applications such as appliance modeling and legislation such as the European General Data Protection Regulation. To address this gap, we propose a novel TSC method - the Randomized-Supervised Time Series Forest (r-STSF). r-STSF is highly efficient, achieves state-of-the-art classification accuracy and enables interpretability. r-STSF takes an efficient interval-based approach to classify time series according to aggregate values of discriminatory sub-series (intervals). To achieve state-of-the-art accuracy, r-STSF builds an ensemble of randomized trees using the discriminatory sub-series. It uses four time series representations, nine aggregation functions and a supervised binary-inspired search combined with a feature ranking metric to identify highly discriminatory sub-series. The discriminatory sub-series enable interpretable classifications. Experiments on extensive datasets show that r-STSF achieves state-of-the-art accuracy while being orders of magnitude faster than most existing TSC methods. It is the only classifier from the state-of-the-art group that enables interpretability. Our findings also highlight that r-STSF is the best TSC method when classifying complex time series datasets.

Personalized promotions A few years ago, promotions were advertised in catalogs or through broadcasts. Both options were rather expensive and displayed the same information for all consumers coming to the store. In supermarkets of the future, AI and advanced analytics offer plenty of information on every individual buyer, such as their meal preferences, food allergies, and motives behind their purchases. By employing AI in grocery personalization, retailers gain extensive knowledge of who is walking down their aisles. This approach enables retailers to craft customized promotions to attract buyers and increase sales.

Amazon today launched SageMaker Reinforcement Learning (RL) Kubeflow Components, a toolkit supporting the company's AWS RoboMaker service for orchestrating robotics workflows. Amazon says that the goal is to make it faster to experiment and manage robotics workloads from perception to controls and optimization, and to create end-to-end solutions without having to rebuild them each time. Robots are being used more widely for purposes that are increasing in sophistication, like assembly, picking and packing, last-mile delivery, environmental monitoring, search and rescue, and assisted surgery. In China, Oxford Economics anticipates 12.5 million manufacturing jobs will become automated, while in the U.S., McKinsey projects that machines will take upwards of 30% of such jobs. As for reinforcement learning, it's an emerging AI technique that can help develop solutions for the kinds of problems that are increasingly cropping up in robotics.

Wikipedia: "Waikato Environment for Knowledge Analysis (Weka), developed at the University of Waikato, New Zealand, is free software licensed under the GNU General Public License, and the companion software to the book "Data Mining: Practical Machine Learning Tools and Techniques". Weka contains a collection of visualization tools and algorithms for data analysis and predictive modeling, together with graphical user interfaces for easy access to these functions. The original non-Java version of Weka was a Tcl/Tk front-end to (mostly third-party) modeling algorithms implemented in other programming languages, plus data preprocessing utilities in C, and a Makefile-based system for running machine learning experiments. This original version was primarily designed as a tool for analyzing data from agricultural domains, but the more recent fully Java-based version (Weka 3), for which development started in 1997, is now used in many different application areas, in particular for educational purposes and research" As the title of the article suggests, WEKA is a tool that will allow you to do Machine Learning without any programming language but using only the GUI of the tool. In this article, we are going to show you how to launch WEKA, and how to start using it, what each of the components means, and help you decide if it is the right tool for your needs.

InteliCare has been awarded a $100,000 grant from the New South Wales Smart Sensing Network ("NSSN") to develop its machine learning (ML) capability in conjunction with the University of Sydney (USyd) and Macquarie University (MU). The company is negotiating an agreement with USyd, MU and the NSSN to use these funds to help fund a one-year joint project delivered by the universities' Computer Science Departments. The goal is to build ML algorithms that can predict and prevent chronic disease and mental health deterioration that can lead to a loss of independence and an increased risk of injury. In addition to the NSSN funds, InteliCare will provide a co-contribution of $152,898 in cash and the universities will provide $161,021 of in-kind support. Ongoing development beyond the initial project will require the company to budget from working capital.

The increased digitalisation and monitoring of the energy system opens up numerous opportunities % and solutions which can help to decarbonise the energy system. Applications on low voltage (LV), localised networks, such as community energy markets and smart storage will facilitate decarbonisation, but they will require advanced control and management. Reliable forecasting will be a necessary component of many of these systems to anticipate key features and uncertainties. Despite this urgent need, there has not yet been an extensive investigation into the current state-of-the-art of low voltage level forecasts, other than at the smart meter level. This paper aims to provide a comprehensive overview of the landscape, current approaches, core applications, challenges and recommendations. Another aim of this paper is to facilitate the continued improvement and advancement in this area. To this end, the paper also surveys some of the most relevant and promising trends. It establishes an open, community-driven list of the known LV level open datasets to encourage further research and development.