It's far less common to see video games tackle the other side of war and competition: the human side. Love, for instance, is rarely a central selling point for a video game. Plenty of classic action and adventure games use love as a motivation for the main character -- usually by kidnapping or killing the male protagonist's wife -- but less often do these experiences dive into the dense complexities of relationships and romance. Wong's latest game, Florence, does just that. It landed on iOS devices this week, just in time for Valentine's Day, and it's the first title out of Wong's Melbourne, Australia, studio, Mountains.

Thank you for your help building out the list!]

Ellerslie grocery shoppers will be the first in the world to trial artificial intelligence technology that will eliminate the need for checkouts. Auckland-based company IMAGR, aims to change the way people shop by using computer vision technology that recognises products as they are placed in the shopping trolley. Foodstuffs' Four Square Ellerslie will be the first fast-moving consumer goods store in the world to trial the Smartcart technology. IMAGR founder William Chomley said he used to spend his whole lunch break waiting in the queue at the supermarket when he worked in Sydney. Working with a team of 12, including artificial intelligence specialists from around the world, Chomley set out to improve the experience of customers.

Our friends over at the Spinoff recently reported that what is predicted to be a driverless future is not all that far off for big little New Zealand. Auckland-based company HMI Technologies who are the people behind Ohmio, have produced self-driving shuttles which are in store for Christchurch Airport in late 2018. The shuttles are electrically powered and operate using self-mapping artificial intelligence. As the shuttle begins to drive it's specified route means, the system will record the coordinates and speed embedding that into how the device is controlled. The shuttle can then replicate that journey and have different routes loaded onto it as needed.

At a mall in Sydney, Australia, "the world's first smart trash can" is fastidiously photographing, weighing, and sorting garbage. The industrious TrashBot is a long way from home. Trashbot was born in Pittsburgh at the AlphaLab Gear startup accelerator. There, the CleanRobotics team has been developing a machine that uses cameras, sensors, and machine learning to ensure that garbage ends up in the landfill and recyclables don't. They're tackling a problem that most environmentalists would agree needs to be solved: only about 20 percent of what goes in those blue bins actually ends up recycled, according to CleanRobotics co-founder Tanner Cook.

The newest artificial intelligence out of San Francisco-based tech firm Aeolus Robotics is a revolutionary robot that can pretty much second guess your family's movements, their identity, and even perform household duties from moping the floor to getting drinks out of the fridge. While the flying cars that were promised to us in The Jetsons are lamentably still on the drawing board, a digital domestic goddess by the likes of Rosie The Robot has actually arrived. The mechanical mate, which is expected to be available by the end of the year, will reportedly cost as much as a car at around $US20,000 ($25,000) and is described by Aeolus as being the height and weight of a 12 year old -- however undoubtedly more house-trained. Just like a creepy scene out of (insert favourite Sci Fi film here) this amazing android can distinguish between family members' faces, recognise where household items are supposed to go (then put them back in place) and can keep a sly eye open for emergencies like a fire or notice a change in posture and possibly prevent a fall. The yet to be officially named "Aeolus Robot" can also move furniture, find lost items and even learn the household schedule via an information sharing network.

We introduce SCAL, an algorithm designed to perform efficient exploration-exploitation in any unknown weakly-communicating Markov Decision Process (MDP) for which an upper bound c on the span of the optimal bias function is known. For an MDP with S states, A actions and Gamma <= S possible next states, we prove a regret bound of O(c\sqrt{Gamma SAT}), which significantly improves over existing algorithms (e.g., UCRL and PSRL), whose regret scales linearly with the MDP diameter D. In fact, the optimal bias span is finite and often much smaller than D (e.g., D=infinity in non-communicating MDPs). A similar result was originally derived by Bartlett and Tewari (2009) for REGAL.C, for which no tractable algorithm is available. In this paper, we relax the optimization problem at the core of REGAL.C, we carefully analyze its properties, and we provide the first computationally efficient algorithm to solve it. Finally, we report numerical simulations supporting our theoretical findings and showing how SCAL significantly outperforms UCRL in MDPs with large diameter and small span.

In this paper, we study the Empirical Risk Minimization problem in the non-interactive local model of differential privacy. We first show that if the ERM loss function is $(\infty, T)$-smooth, then we can avoid a dependence of the sample complexity, to achieve error $\alpha$, on the exponential of the dimensionality $p$ with base $1/\alpha$ ({\em i.e.,} $\alpha^{-p}$), which answers a question in \cite{smith2017interaction}. Our approach is based on Bernstein polynomial approximation. Then, we propose player-efficient algorithms with $1$-bit communication complexity and $O(1)$ computation cost for each player. The error bound is asymptotically the same as the original one. Also with additional assumptions we show a server efficient algorithm with polynomial running time. At last, we propose (efficient) non-interactive locally differential private algorithms, based on different types of polynomial approximations, for learning the set of k-way marginal queries and the set of smooth queries.

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to adversarial examples. This work is one of the most proactive approaches taken to date, as we link robustness with non-calibrated model confidence on noisy images, providing a data-augmentation-free path forward. The adversarial examples phenomenon is most easily explained by the trend of increasing non-regularized model capacity, while the diversity and number of samples in common datasets has remained flat. Test accuracy has incorrectly been associated with true generalization performance, ignoring that training and test splits are often extremely similar in terms of the overall representation space. The transferability property of adversarial examples was previously used as evidence against overfitting arguments, a perceived random effect, but overfitting is not always random.

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.