A teenager in New South Wales recently died after a fatal shark bite, adding to four other unprovoked shark-related deaths this year. These tragic events send shockwaves through the community and re-ignite our fear of sharks. They also fuel the debate around the best way to keep people safe in the water while minimising impacts on marine wildlife. This was the aim of a five-year trial of shark-mitigation technology--the Shark Management Strategy – which finished recently. The NSW government created this initiative in response to an unprecedented spike in shark bites in 2015, particularly on the north coast of NSW.

While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same task. In this work, we propose to solve such a few-shot (or low-shot) visual reasoning problem, by resorting to analogical reasoning, which is a unique human ability to identify structural or relational similarity between two sets. Specifically, given training and test sets that contain the same type of visual reasoning problems, we extract the structural relationships between elements in both domains, and enforce them to be as similar as possible with analogical learning. We repeatedly apply this process with slightly modified queries of the same problem under the assumption that it does not affect the relationship between a training and a test sample. This allows to learn the relational similarity between the two samples in an effective manner even with a single pair of samples. We validate our method on RAVEN dataset, on which it outperforms state-of-the-art method, with larger gains when the training data is scarce. We further meta-learn our analogical contrastive learning model over the same tasks with diverse attributes, and show that it generalizes to the same visual reasoning problem with unseen attributes.

Designing task-oriented dialogue systems is a challenging research topic, since it needs not only to generate utterances fulfilling user requests but also to guarantee the comprehensibility. Many previous works trained end-to-end (E2E) models with supervised learning (SL), however, the bias in annotated system utterances remains as a bottleneck. Reinforcement learning (RL) deals with the problem through using non-differentiable evaluation metrics (e.g., the success rate) as rewards. Nonetheless, existing works with RL showed that the comprehensibility of generated system utterances could be corrupted when improving the performance on fulfilling user requests. In our work, we (1) propose modelling the hierarchical structure between dialogue policy and natural language generator (NLG) with the option framework, called HDNO; (2) train HDNO with hierarchical reinforcement learning (HRL), as well as suggest alternating updates between dialogue policy and NLG during HRL inspired by fictitious play, to preserve the comprehensibility of generated system utterances while improving fulfilling user requests; and (3) propose using a discriminator modelled with language models as an additional reward to further improve the comprehensibility. We test HDNO on MultiWoz 2.0 and MultiWoz 2.1, the datasets on multi-domain dialogues, in comparison with word-level E2E model trained with RL, LaRL and HDSA, showing a significant improvement on the total performance evaluated with automatic metrics.

In this paper we investigate problematic practices and consequences of large scale vision datasets. We examine broad issues such as the question of consent and justice as well as specific concerns such as the inclusion of verifiably pornographic images in datasets. Taking the ImageNet-ILSVRC-2012 dataset as an example, we perform a cross-sectional model-based quantitative census covering factors such as age, gender, NSFW content scoring, class-wise accuracy, human-cardinality-analysis, and the semanticity of the image class information in order to statistically investigate the extent and subtleties of ethical transgressions. We then use the census to help hand-curate a look-up-table of images in the ImageNet-ILSVRC-2012 dataset that fall into the categories of verifiably pornographic: shot in a non-consensual setting (up-skirt), beach voyeuristic, and exposed private parts. We survey the landscape of harm and threats both society broadly and individuals face due to uncritical and ill-considered dataset curation practices. We then propose possible courses of correction and critique the pros and cons of these. We have duly open-sourced all of the code and the census meta-datasets generated in this endeavor for the computer vision community to build on. By unveiling the severity of the threats, our hope is to motivate the constitution of mandatory Institutional Review Boards (IRB) for large scale dataset curation processes.

Differentially private GANs have proven to be a promising approach for generating realistic synthetic data without compromising the privacy of individuals. However, due to the privacy-protective noise introduced in the training, the convergence of GANs becomes even more elusive, which often leads to poor utility in the output generator at the end of training. We propose Private post-GAN boosting (Private PGB), a differentially private method that combines samples produced by the sequence of generators obtained during GAN training to create a high-quality synthetic dataset. Our method leverages the Private Multiplicative Weights method (Hardt and Rothblum, 2010) and the discriminator rejection sampling technique (Azadi et al., 2019) for reweighting generated samples, to obtain high quality synthetic data even in cases where GAN training does not converge. We evaluate Private PGB on a Gaussian mixture dataset and two US Census datasets, and demonstrate that Private PGB improves upon the standard private GAN approach across a collection of quality measures. Finally, we provide a non-private variant of PGB that improves the data quality of standard GAN training.

Many learning tasks involve multi-modal data streams, where continuous data from different modes convey a comprehensive description about objects. A major challenge in this context is how to efficiently interpret multi-modal information in complex environments. This has motivated numerous studies on learning unsupervised representations from multi-modal data streams. These studies aim to understand higher-level contextual information (e.g., a Twitter message) by jointly learning embeddings for the lower-level semantic units in different modalities (e.g., text, user, and location of a Twitter message). However, these methods directly associate each low-level semantic unit with a continuous embedding vector, which results in high memory requirements. Hence, deploying and continuously learning such models in low-memory devices (e.g., mobile devices) becomes a problem. To address this problem, we present METEOR, a novel MEmory and Time Efficient Online Representation learning technique, which: (1) learns compact representations for multi-modal data by sharing parameters within semantically meaningful groups and preserves the domain-agnostic semantics; (2) can be accelerated using parallel processes to accommodate different stream rates while capturing the temporal changes of the units; and (3) can be easily extended to capture implicit/explicit external knowledge related to multi-modal data streams. We evaluate METEOR using two types of multi-modal data streams (i.e., social media streams and shopping transaction streams) to demonstrate its ability to adapt to different domains. Our results show that METEOR preserves the quality of the representations while reducing memory usage by around 80% compared to the conventional memory-intensive embeddings.

An online app called Amica is now using artificial intelligence to help separating couples make parenting arrangements and divide their assets. For many people, the coronavirus pandemic has put even the strongest of relationships to the test. A May survey conducted by Relationships Australia found 42% of 739 respondents experienced a negative change in their relationship with their partner under lockdown restrictions. There has also been a surge in the number of couples seeking separation advice. The Australian government has backed the use of Amica for those in such circumstances.

Nintex, the global standard for process management and automation, has announced the organization has been honored as one of Australia's Best Places to Work in 2020 based on recently published employee survey data from Great Places to Work, an independent research firm. This year's Great Place to Work benchmarking study included nearly 40,000 Australian-based employees representing 124 companies. Designed to evaluate employee engagement and trust levels across Australian workplaces, the 2020 study process also provides visibility into how organizations are inspiring, inventing, and innovating with new initiatives whilst navigating through a changing landscape due to COVID-19. "We're honored to be recognized as one of Australia's best places to work which is especially meaningful in these unprecedented times," says Nintex Vice President of APAC Sales Christian Lucarelli. "At Nintex, we believe that people are most important. We care for our team members and treat each other with respect and consideration at all times, and it's also how we interact with every customer and partner who are part of our growing global Nintex community."

When Whakaari (White Island) in New Zealand unexpectedly erupted in December 2019, more than 40 tourists found themselves trapped on a small island that was exploding. The hot gases and water, flying rocks and ash killed 21 people during that eruption. This tragedy was a wake-up call for tour operators who would regularly bring people to this restless volcano in the Bay of Plenty. It is a volcano that produces steam-driven explosions that come with little warning, and it is these types of blasts that have killed dozens of people on volcanoes around the world over the past decade. Part of the problem is how we think about volcanic danger.

Researchers from Massey University, the University of Tasmania and Stetson University reviewed multiple long-term studies into video games and aggression. They found no evidence of a substantial link between'aggressive game content' and signs of anger or rage later on in childhood. 'Poor quality studies' in the past likely exaggerated the impact of games on aggression, while better quality studies show the effects of gaming are'negligible'. Regulation of violent games also did not appear likely to reduce aggression in real life, suggesting parents shouldn't worry about their kids shooting up virtual enemies. Real-life displays of violence, such as mass shootings in the US, have famously been blamed on video games by some politicians, rather than lax gun regulation and easy access to firearms.