This paper presents c2g-HOF networks which learn to generate cost-to-go functions for manipulator motion planning. The c2g-HOF architecture consists of a cost-to-go function over the configuration space represented as a neural network (c2g-network) as well as a Higher Order Function (HOF) network which outputs the weights of the c2g-network for a given input workspace. Both networks are trained end-to-end in a supervised fashion using costs computed from traditional motion planners. Once trained, c2g-HOF can generate a smooth and continuous cost-to-go function directly from workspace sensor inputs (represented as a point cloud in 3D or an image in 2D). At inference time, the weights of the c2g-network are computed very efficiently and near-optimal trajectories are generated by simply following the gradient of the cost-to-go function. We compare c2g-HOF with traditional planning algorithms for various robots and planning scenarios. The experimental results indicate that planning with c2g-HOF is significantly faster than other motion planning algorithms, resulting in orders of magnitude improvement when including collision checking. Furthermore, despite being trained from sparsely sampled trajectories in configuration space, c2g-HOF generalizes to generate smoother, and often lower cost, trajectories. We demonstrate cost-to-go based planning on a 7 DoF manipulator arm where motion planning in a complex workspace requires only 0.13 seconds for the entire trajectory.

Our title alludes to the three Christmas ghosts encountered by Ebenezer Scrooge in \textit{A Christmas Carol}, who guide Ebenezer through the past, present, and future of Christmas holiday events. Similarly, our article will take readers through a journey of the past, present, and future of medical AI. In doing so, we focus on the crux of modern machine learning: the reliance on powerful but intrinsically opaque models. When applied to the healthcare domain, these models fail to meet the needs for transparency that their clinician and patient end-users require. We review the implications of this failure, and argue that opaque models (1) lack quality assurance, (2) fail to elicit trust, and (3) restrict physician-patient dialogue. We then discuss how upholding transparency in all aspects of model design and model validation can help ensure the reliability of medical AI.

Deep neural network models represent the state-of-the-art methodologies for natural language processing. Here we build on top of these methodologies to incorporate temporal information and model how to review data changes with time. Specifically, we use the dynamic representations of recurrent point process models, which encode the history of how business or service reviews are received in time, to generate instantaneous language models with improved prediction capabilities. Simultaneously, our methodologies enhance the predictive power of our point process models by incorporating summarized review content representations. We provide recurrent network and temporal convolution solutions for modeling the review content. We deploy our methodologies in the context of recommender systems, effectively characterizing the change in preference and taste of users as time evolves. Source code is available at [1].

We emphasize the importance of asking the right question when interpreting the decisions of a learning model. We discuss a natural extension of the theoretical machinery from Janzing et. al. 2020, which answers the question "Why did my model predict a person has cancer?" for answering a more involved question, "What caused my model to predict a person has cancer?" While the former quantifies the direct effects of variables on the model, the latter also accounts for indirect effects, thereby providing meaningful insights wherever human beings can reason in terms of cause and effect. We propose three broad categories for interpretations: observational, model-specific and causal each of which are significant in their own right. Furthermore, this paper quantifies feature relevance by weaving different natures of interpretations together with different measures as characteristic functions for Shapley symmetrization. Besides the widely used expected value of the model, we also discuss measures of statistical uncertainty and dispersion as informative candidates, and their merits in generating explanations for each data point, some of which are used in this context for the first time. These measures are not only useful for studying the influence of variables on the model output, but also on the predictive performance of the model, and for that we propose relevant characteristic functions that are also used for the first time.

Marc Peter Deisenroth is DeepMind Chair in Artificial Intelligence at the Department of Computer Science, University College London. Prior to this, he was a faculty member in the Department of Computing, Imperial College London. His research areas include data-efficient learning, probabilistic modeling, and autonomous decision making. Deisenroth was Program Chair of the European Workshop on Reinforcement Learning (EWRL) 2012 and Workshops Chair of Robotics Science and Systems (RSS) 2013. His research received Best Paper Awards at the International Conference on Robotics and Automation (ICRA) 2014 and the International Conference on Control, Automation and Systems (ICCAS) 2016.

In many ways, artificial intelligence (AI) is already affecting organisations and the way we work. As such, businesses need to be able to respond to AI and harness big data to make decisions that benefit employees, customers and shareholders. So what challenges and opportunities does AI create for business leaders today? How business leaders can utilise AI today and prepare for its future is discussed in part two of The Business of Transformational Leadership, the ninth episode of the AGSM @ UNSW Business School Leadership Podcast series. In the podcast, Host Emma LoRusso, CEO and Co-founder of Digivizer, who completed an AGSM MBA (Executive) in 2013, is joined by Toby Walsh, Scientia Professor of AI in the School of Computer Science and Engineering at UNSW Sydney. He also leads the algorithmic decision theory group at CSIRO's digital research network, Data61.

Artificial intelligence tools that seek to address complex public problems need to be developed with the input of the decision-makers who will implement them, Mitzi Bolton writes. Turn on the news, social media, or catch up with friends and you'll no doubt find conversations turning to the problems of society, things that could or should be done differently. Things the government ought to fix but seems unable to address. There's the risk of exceeding planetary boundaries, increased incidence of zoonotic diseases, climate change and its related impacts, continuing debates over management of the Murray Darling Basin, disincentives to workforce participation, handling of hotel quarantine, and many more. These and other highly challenging problems, often considered in isolation, come together when global progress on the Sustainable Development Goals (SDGs) is considered.

Surfers know they share the waters they love with sharks, but technology may soon offer some added protection from a possible encounter. According to Southern Cross University researcher Andrew Colefax, the day is nearing that autonomous drones -- which do not require a line-of-sight operator -- will be able to offer shark detection at any point along the coastline. "I feel like that's around the corner," Dr Colefax said. He has spent four years of intense research and development in the field of drones and shark detection, and said artificial intelligence (AI) and machine learning will be a game changer on beaches in the near future. "There is continual research in this method to make it more reliable and provide a better level of safety," Dr Colefax said.

Joy Buolamwini from the MIT Media Lab says facial-recognition software has the highest error rates for darker-skinned females. New applications powered by artificial intelligence (AI) are being embraced by the public and private sectors. Their early uses hint at what's to come. In June 2020, IBM, Amazon and Microsoft announced that they were stepping back from facial-recognition software development amid concerns that it reinforces racial and gender bias. Amazon and Microsoft said they would stop selling facial-recognition software to police until new laws are passed in the United States to address potential human-rights abuses.

Growing research demonstrates that synthetic failure modes imply poor generalization. We compare commonly used audio-to-audio losses on a synthetic benchmark, measuring the pitch distance between two stationary sinusoids. The results are surprising: many have poor sense of pitch direction. These shortcomings are exposed using simple rank assumptions. Our task is trivial for humans but difficult for these audio distances, suggesting significant progress can be made in self-supervised audio learning by improving current losses.