Our third interview is with Sid Dutta of MD APAC Kantar Profiles Division, Nuchy Tungwarapojwitan of MD Intage Thailand, and Joel Vermaas of Nature Research Australia. Watch how they collaboratively share some insightful information about the future of research and how AI can change everything. For more episodes of APACInsight, make sure to subscribe to our channel. Use this code "INNOVATION30" to save 30% on your ticket.

China is selling its most advanced "fully autonomous" military drones with fears that it could lead to a bloodbath in the Middle East. The Asian superpower is reportedly selling AI-enhanced combat drones to the region, with potentially disastrous consequences. Prof Toby Walsh, of the University of NSW, in Australia, said: "They would be impossible to defend yourself against. "Once the shooting starts, every human on the battlefield will be dead." US Defence Sec Mark Esper has said that China is selling drones programmed to decide themselves who lives or dies. He told a conference on Artificial Intelligence: "As we speak, the Chinese government is already exporting some of its most advanced military aerial drones to the Middle East as it prepares to export its next generation stealth UAVs when those come online.

Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast arrayof these resources, most under-resourced languages do not, especially for fine-grained sentiment tasks, such as aspect-level or targeted sentiment analysis. To improve this situation, we propose a cross-lingual approach to sentiment analysis that is applicable to under-resourced languages and takes into account target-level information. This model incorporates sentiment information into bilingual distributional representations, byjointly optimizing them for semantics and sentiment, showing state-of-the-art performance at sentence-level when combined with machine translation. The adaptation to targeted sentiment analysis on multiple domains shows that our model outperforms other projection-based bilingual embedding methods on binary targetedsentiment tasks. Our analysis on ten languages demonstrates that the amount of unlabeled monolingual data has surprisingly little effect on the sentiment results. As expected, the choice of a annotated source language for projection to a target leads to better results for source-target language pairs which are similar. Therefore, our results suggest that more efforts should be spent on the creation of resources for less similar languages tothose which are resource-rich already. Finally, a domain mismatch leads to a decreased performance. This suggests resources in any language should ideally cover varieties of domains.

An approach to distributed machine learning is to train models on local datasets and aggregate these models into a single, stronger model. A popular instance of this form of parallelization is federated learning, where the nodes periodically send their local models to a coordinator that aggregates them and redistributes the aggregation back to continue training with it. The most frequently used form of aggregation is averaging the model parameters, e.g., the weights of a neural network. However, due to the non-convexity of the loss surface of neural networks, averaging can lead to detrimental effects and it remains an open question under which conditions averaging is beneficial. In this paper, we study this problem from the perspective of information theory: We measure the mutual information between representation and inputs as well as representation and labels in local models and compare it to the respective information contained in the representation of the averaged model. Our empirical results confirm previous observations about the practical usefulness of averaging for neural networks, even if local dataset distributions vary strongly. Furthermore, we obtain more insights about the impact of the aggregation frequency on the information flow and thus on the success of distributed learning. These insights will be helpful both in improving the current synchronization process and in further understanding the effects of model aggregation.

Correctly pricing products or services in an online marketplace presents a challenging problem and one of the critical factors for the success of the business. When users are looking to buy an item they typically search for it. Query relevance models are used at this stage to retrieve and rank the items on the search page from most relevant to least relevant. The presented items are naturally "competing" against each other for user purchases. We provide a practical two-stage model to price this set of retrieved items for which distributions of their values are learned. The initial output of the pricing strategy is a price vector for the top displayed items in one search event. We later aggregate these results over searches to provide the supplier with the optimal price for each item. We applied our solution to large-scale search data obtained from Airbnb Experiences marketplace. Offline evaluation results show that our strategy improves upon baseline pricing strategies on key metrics by at least +20% in terms of booking regret and +55% in terms of revenue potential.

We study distributed stochastic gradient (D-SG) method and its accelerated variant (D-ASG) for solving decentralized strongly convex stochastic optimization problems where the objective function is distributed over several computational units, lying on a fixed but arbitrary connected communication graph, subject to local communication constraints where noisy estimates of the gradients are available. We develop a framework which allows to choose the stepsize and the momentum parameters of these algorithms in a way to optimize performance by systematically trading off the bias, variance, robustness to gradient noise and dependence to network effects. When gradients do not contain noise, we also prove that distributed accelerated methods can \emph{achieve acceleration}, requiring $\mathcal{O}(\kappa \log(1/\varepsilon))$ gradient evaluations and $\mathcal{O}(\kappa \log(1/\varepsilon))$ communications to converge to the same fixed point with the non-accelerated variant where $\kappa$ is the condition number and $\varepsilon$ is the target accuracy. To our knowledge, this is the first acceleration result where the iteration complexity scales with the square root of the condition number in the context of \emph{primal} distributed inexact first-order methods. For quadratic functions, we also provide finer performance bounds that are tight with respect to bias and variance terms. Finally, we study a multistage version of D-ASG with parameters carefully varied over stages to ensure exact $\mathcal{O}(-k/\sqrt{\kappa})$ linear decay in the bias term as well as optimal $\mathcal{O}(\sigma^2/k)$ in the variance term. We illustrate through numerical experiments that our approach results in practical algorithms that are robust to gradient noise and that can outperform existing methods.

Due to the increasing use of machine learning in practice it becomes more and more important to be able to explain the pred iction and behavior of machine learning models. An instance of expl anations are counterfactual explanations which provide an intuitive an d useful explanations of machine learning models. In this survey we review model-specific methods for efficientl y computing counterfactual explanations of many different machine learning models and propose methods for models that have not been considered in l iterature so far.

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on machine learning models in the visual domain, where methods for generating and detecting such examples have been most extensively studied. We explore a variety of adversarial attack methods that apply to image-space content, real world adversarial attacks, adversarial defenses, and the transferability property of adversarial examples. We also discuss strengths and weaknesses of various methods of adversarial attack and defense. Our aim is to provide an extensive coverage of the field, furnishing the reader with an intuitive understanding of the mechanics of adversarial attack and defense mechanisms and enlarging the community of researchers studying this fundamental set of problems.

Artificial Intelligence: Solving problems, growing the economy and improving our quality of life outlines the importance of action for Australia to capture the benefits of artificial intelligence (AI), estimated to be worth AU$22.17 Published by the Australian Government in November 2019, and codeveloped by CSIRO's Data61 and the Department of Industry, Innovation and Science, the report identifies strategies to help develop a national AI capability to boost the productivity of Australian industry, create jobs and economic growth, and improve the quality of life for current and future generations. The roadmap identifies three high potential areas of AI specialisation for Australia based on the opportunity to solve significant problems at home, export the solutions to the world and build on Australia's existing strengths. This report is intended to help guide future investment in AI and machine learning, and accompanies Artificial Intelligence: Australia's Ethics Framework, a discussion paper prepared by CSIRO's Data61 and published by the Australian Government in April 2019.

After breakfast one morning in August, the mathematician Terence Tao opened an email from three physicists he didn't know. The trio explained that they'd stumbled across a simple formula that, if true, established an unexpected relationship between some of the most basic and important objects in linear algebra. The formula "looked too good to be true," said Tao, who is a professor at the University of California, Los Angeles, a Fields medalist, and one of the world's leading mathematicians. "Something this short and simple -- it should have been in textbooks already," he said. "So my first thought was, no, this can't be true."