Within the realm of service robotics, researchers have placed a great amount of effort into learning motions and manipulations for task execution by robots. The task of robot learning is very broad, as it involves many tasks such as object detection, action recognition, motion planning, localization, knowledge representation and retrieval, and the intertwining of computer vision and machine learning techniques. In this paper, we focus on how knowledge can be gathered, represented, and reproduced to solve problems as done by researchers in the past decades. We discuss the problems which have existed in robot learning and the solutions, technologies or developments (if any) which have contributed to solving them. Specifically, we look at three broad categories involved in task representation and retrieval for robotics: 1) activity recognition from demonstrations, 2) scene understanding and interpretation, and 3) task representation in robotics - datasets and networks. Within each section, we discuss major breakthroughs and how their methods address present issues in robot learning and manipulation.

Stochastic video prediction is usually framed as an extrapolation problem where the goal is to sample a sequence of consecutive future image frames conditioned on a sequence of observed past frames. For the most part, algorithms for this task generate future video frames sequentially in an autoregressive fashion, which is slow and requires the input and output to be consecutive. We introduce a model that overcomes these drawbacks -- it learns to generate a global latent representation from an arbitrary set of frames within a video. This representation can then be used to simultaneously and efficiently sample any number of temporally consistent frames at arbitrary time-points in the video. We apply our model to synthetic video prediction tasks and achieve results that are comparable to state-of-the-art video prediction models. In addition, we demonstrate the flexibility of our model by applying it to 3D scene reconstruction where we condition on location instead of time. To the best of our knowledge, our model is the first to provide flexible and coherent prediction on stochastic video datasets, as well as consistent 3D scene samples. Please check the project website https://bit.ly/2jX7Vyu to view scene reconstructions and videos produced by our model.

The job-destroying potential of artificial intelligence and automation has created much angst around the fast-evolving technology. How will we be affected and what industries and regions are likely to be hit hardest? Much needed research into the issue is starting to emerge, but the widely varying estimates on the job-destroying potential of AI and automation shows just how difficult it is to predict the impact of this potentially highly disruptive technology across the economy and society. A critical question to answer is whether artificial intelligence will be as significantly disruptive to employment as previous transformative technologies, such as electricity and the internet were. Another key question to unpick is what timeframe the transformation will occur over.

While artificial intelligence (AI) continues to develop at an astronomical pace, one of the most pressing questions is how to stop human bias getting "baked into" algorithms. Speaking at B&T's inaugural Breakfast Club this morning presented by Adobe, Adobe director of digital marketing Michael Stoddart said despite our control, algorithms are not neutral by their very nature. The impact of this is problematic bias, often resulting in conditioned sexism, according to Stoddart. Stoddart referred back to an algorithm where a "computer to man" was likened to "homemakers to women". For Stoddart, biases which are inherent in society can often be translated into technology.

Young scientists from the University of Auckland and Victoria University of Wellington have come up with a novel way to figure out which party or parties in New Zealand's Parliament are dominating any particular political debate or discourse. Young scientists from the University of Auckland and Victoria University of Wellington have come up with a novel way to figure out which party or parties in New Zealand's Parliament are dominating any particular political debate or discourse. Te Pūnaha Matatini Whanau members Ben Curran and Demival Vasques Filho (University of Auckland), and Kyle Higham and Elisenda Ortiz (Victoria University of Wellington) collaborated on the project, and their research findings have just been published in PLoS ONE, a leading international scientific journal. Their paper, 'Look who's talking: Two-mode networks as representations of a topic model of New Zealand Parliamentary speeches,' shows how the popularity of different topics debated in Parliament change over time, and proposes an approach that can reveal which party or parties are dominating the debate within certain topics. "It is difficult for any society to simply and easily track political debate and discussion over time," says co-author Demival Vasques Filho.

Differential privacy comes equipped with multiple analytical tools for the design of private data analyses. One important tool is the so called "privacy amplification by subsampling" principle, which ensures that a differentially private mechanism run on a random subsample of a population provides higher privacy guarantees than when run on the entire population. Several instances of this principle have been studied for different random subsampling methods, each with an ad-hoc analysis. In this paper we present a general method that recovers and improves prior analyses, yields lower bounds and derives new instances of privacy amplification by subsampling. Our method leverages a characterization of differential privacy as a divergence which emerged in the program verification community. Furthermore, it introduces new tools, including advanced joint convexity and privacy profiles, which might be of independent interest.

Domestic Violence (DV) is considered as big social issue and there exists a strong relationship between DV and health impacts of the public. Existing research studies have focused on social media to track and analyse real world events like emerging trends, natural disasters, user sentiment analysis, political opinions, and health care. However there is less attention given on social welfare issues like DV and its impact on public health. Recently, the victims of DV turned to social media platforms to express their feelings in the form of posts and seek the social and emotional support, for sympathetic encouragement, to show compassion and empathy among public. But, it is difficult to mine the actionable knowledge from large conversational datasets from social media due to the characteristics of high dimensions, short, noisy, huge volume, high velocity, and so on. Hence, this paper will propose a novel framework to model and discover the various themes related to DV from the public domain. The proposed framework would possibly provide unprecedentedly valuable information to the public health researchers, national family health organizations, government and public with data enrichment and consolidation to improve the social welfare of the community. Thus provides actionable knowledge by monitoring and analysing continuous and rich user generated content.

A world's first QUT-led study has used artificial intelligence to analyse regional personality characteristics estimated solely from language patterns in 1.5 billion Twitter posts and uncover hotspots and cold spots of entrepreneurial personality and activity across the US. QUT's Associate Professor Martin Obschonka from the Australian Centre for Entrepreneurship Research teamed up with researchers from the London School of Economics and Political Science, the University of Pennsylvania and the University of Mannheim. Their paper, Big Data, artificial intelligence and the geography of entrepreneurship in the United States has just been published online via the Centre for Economic Policy Research (London, UK) and the Center for Open Science (Charlottesville, USA). Professor Obschonka said the study proved a Twitter-based personality estimate is as successful in predicting local differences in actual entrepreneurial activity (e.g., local start-up rates) as regional personality data collected by means of millions of standard personality tests. "What we have discovered here is that social media – how language is used in Twitter - is a reliable marker of economic vitality in a region," Professor Obschonka said.

Australia's top cyber spy says the world needs to think more about risks created by over-reliance on artificial intelligence so that people don't "sleepwalk" into dependence on machines they don't actually understand. In an rare public speech, Mike Burgess, Director-General of the Australian Signals Directorate, also said spy agencies around the world - including his own - were increasingly using artificial intelligence to carry out their covert activities. "It is right the world embraces artificial intelligence, but we must embrace this with our eyes wide open. We should not sleepwalk into this, where we suddenly find ourselves in the world that is controlled by software and very few people understand how it works," Mr Burgess told a conference on artificial intelligence hosted by the Australian Strategic Policy Institute. "How much of our world will be outsourced AI? How much of our brain power and decision-making will we hand over?

A number of problems in relational Artificial Intelligence can be viewed as Stochastic Constraint Optimization Problems (SCOPs). These are constraint optimization problems that involve objectives or constraints with a stochastic component. Building on the recently proposed language SC-ProbLog for modeling SCOPs, we propose a new method for solving these problems. Earlier methods used Probabilistic Logic Programming (PLP) techniques to create Ordered Binary Decision Diagrams (OBDDs), which were decomposed into smaller constraints in order to exploit existing constraint programming (CP) solvers. We argue that this approach has as drawback that a decomposed representation of an OBDD does not guarantee domain consistency during search, and hence limits the efficiency of the solver. For the specific case of monotonic distributions, we suggest an alternative method for using CP in SCOP, based on the development of a new propagator; we show that this propagator is linear in the size of the OBDD, and has the potential to be more efficient than the decomposition method, as it maintains domain consistency.