What is the best simulation tool for robotics? This is a hard question to answer because many people (or their companies) specialize in one tool or another. Some simulators are better at one aspect of robotics than at others. When I'm asked to recommend the best simulation tool for robotics I have to find an expert and hope that they are current and across a wide range of simulation tools in order to give me the best advice, which was why I took particular note of the recent review paper from Australia's CSIRO, "A Review of Physics Simulators for Robotics Applications" by Jack Collins, Shelvin Chand, Anthony Vanderkop, and David Howard, published in IEEE Access (Volume: 9). "We have compiled a broad review of physics simulators for use within the major fields of robotics research. More specifically, we navigate through key sub-domains and discuss the features, benefits, applications and use-cases of the different simulators categorised by the respective research communities. Our review provides an extensive index of the leading physics simulators applicable to robotics researchers and aims to assist them in choosing the best simulator for their use case."

Over the last few months here at Carnegie Mellon University (Australia campus) I've been giving a set of talks on AI and the great leaps it has made in the last 5 or so years. I focus on disruptive technologies and give examples ranging from smart fridges and jackets to autonomous cars, robots, and drones. The title of one of my talks is "AI and the 4th Industrial Revolution". Indeed, we are living in the 4th industrial revolution – a significant time in the history of mankind. The first revolution occurred in the 18th century with the advent of mechanisation and steam power; the second came about 100 years later with the discovery of electrical energy (among other things); and the big one, the 3rd industrial revolution, occurred another 100 years after that (roughly around the 1970s) with things like nuclear energy, space expeditions, electronics, telecommunications, etc. coming to the fore. So, yes, we are living in a significant time.

Despite being designed for performance rather than cognitive plausibility, transformer language models have been found to be better at predicting metrics used to assess human language comprehension than language models with other architectures, such as recurrent neural networks. Based on how well they predict the N400, a neural signal associated with processing difficulty, we propose and provide evidence for one possible explanation - their predictions are affected by the preceding context in a way analogous to the effect of semantic facilitation in humans.

We present a new dataset of Wikipedia articles each paired with a knowledge graph, to facilitate the research in conditional text generation, graph generation and graph representation learning. Existing graph-text paired datasets typically contain small graphs and short text (1 or few sentences), thus limiting the capabilities of the models that can be learned on the data. Our new dataset WikiGraphs is collected by pairing each Wikipedia article from the established WikiText-103 benchmark (Merity et al., 2016) with a subgraph from the Freebase knowledge graph (Bollacker et al., 2008). This makes it easy to benchmark against other state-of-the-art text generative models that are capable of generating long paragraphs of coherent text. Both the graphs and the text data are of significantly larger scale compared to prior graph-text paired datasets. We present baseline graph neural network and transformer model results on our dataset for 3 tasks: graph -> text generation, graph -> text retrieval and text -> graph retrieval. We show that better conditioning on the graph provides gains in generation and retrieval quality but there is still large room for improvement.

For that, we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic's score of a high score image and increase the critic's score of a low score image by swapping the masked areas between these two images. We trained the model on an imitation learning dataset from the NeurIPS 2020 MineRL Competition Track, where our model learned to mask rewarding objects in a complex interactive 3D environment with a sparse reward signal. This approach was part of the 1st place winning solution in this competition.

We extend the theory of PAC learning in a way which allows to model a rich variety of learning tasks where the data satisfy special properties that ease the learning process. For example, tasks where the distance of the data from the decision boundary is bounded away from zero. The basic and simple idea is to consider partial concepts: these are functions that can be undefined on certain parts of the space. When learning a partial concept, we assume that the source distribution is supported only on points where the partial concept is defined. This way, one can naturally express assumptions on the data such as lying on a lower dimensional surface or margin conditions. In contrast, it is not at all clear that such assumptions can be expressed by the traditional PAC theory. In fact we exhibit easy-to-learn partial concept classes which provably cannot be captured by the traditional PAC theory. This also resolves a question posed by Attias, Kontorovich, and Mansour 2019. We characterize PAC learnability of partial concept classes and reveal an algorithmic landscape which is fundamentally different than the classical one. For example, in the classical PAC model, learning boils down to Empirical Risk Minimization (ERM). In stark contrast, we show that the ERM principle fails in explaining learnability of partial concept classes. In fact, we demonstrate classes that are incredibly easy to learn, but such that any algorithm that learns them must use an hypothesis space with unbounded VC dimension. We also find that the sample compression conjecture fails in this setting. Thus, this theory features problems that cannot be represented nor solved in the traditional way. We view this as evidence that it might provide insights on the nature of learnability in realistic scenarios which the classical theory fails to explain.

All the sessions from Transform 2021 are available on-demand now. Over the next two years, 75% of finance professionals believe their day jobs will significantly change, and 83% said they will have to learn new skills for AI and related technologies, according to a survey of finance processionals around the world from Unit4, a cloud leader in enterprise software. Above: More technical knowledge may be helpful, but the survey shows a surprising lack of emphasis on strategic leadership skills; only a quarter say interpersonal and influencing will be essential for future finance professionals. And only 21% think story telling will be important. In the next 12 months, more than four fifths of respondents are expecting to focus this upskilling on AI, machine learning, coding, analytics and data science capabilities, but a third of respondents accept that their organizations will need to grow their teams to fully implement the new technology, Unit4 said.

Prostate cancer is the most diagnosed cancer and a leading cause of death by cancer in Australian men. Early detection is key to successful treatment but men often dodge the doctor, avoiding diagnosis tests until it's too late. Now an artificial intelligence (AI) program developed at RMIT University could catch the disease earlier, allowing for incidental detection through routine computed tomography (CT) scans. The tech, developed in collaboration with clinicians at St Vincent's Hospital Melbourne, works by analysing CT scans for tell-tale signs of prostate cancer, something even a well-trained human eye struggles to do. CT imaging is not suitable for regular cancer screening because of the high radiation doses involved, but the AI solution could be used to run a cancer check whenever men have their abdomen or pelvis scanned for other issues.

Physiological motion, such as cardiac and respiratory motion, during Magnetic Resonance (MR) image acquisition can cause image artifacts. Motion correction techniques have been proposed to compensate for these types of motion during thoracic scans, relying on accurate motion estimation from undersampled motion-resolved reconstruction. A particular interest and challenge lie in the derivation of reliable non-rigid motion fields from the undersampled motion-resolved data. Motion estimation is usually formulated in image space via diffusion, parametric-spline, or optical flow methods. However, image-based registration can be impaired by remaining aliasing artifacts due to the undersampled motion-resolved reconstruction. In this work, we describe a formalism to perform non-rigid registration directly in the sampled Fourier space, i.e. k-space. We propose a deep-learning based approach to perform fast and accurate non-rigid registration from the undersampled k-space data. The basic working principle originates from the Local All-Pass (LAP) technique, a recently introduced optical flow-based registration. The proposed LAPNet is compared against traditional and deep learning image-based registrations and tested on fully-sampled and highly-accelerated (with two undersampling strategies) 3D respiratory motion-resolved MR images in a cohort of 40 patients with suspected liver or lung metastases and 25 healthy subjects. The proposed LAPNet provided consistent and superior performance to image-based approaches throughout different sampling trajectories and acceleration factors.

AI in finance broadly refers to the applications of AI techniques in financial businesses. This area has been lasting for decades with both classic and modern AI techniques applied to increasingly broader areas of finance, economy and society. In contrast to either discussing the problems, aspects and opportunities of finance that have benefited from specific AI techniques and in particular some new-generation AI and data science (AIDS) areas or reviewing the progress of applying specific techniques to resolving certain financial problems, this review offers a comprehensive and dense roadmap of the overwhelming challenges, techniques and opportunities of AI research in finance over the past decades. The landscapes and challenges of financial businesses and data are firstly outlined, followed by a comprehensive categorization and a dense overview of the decades of AI research in finance. We then structure and illustrate the data-driven analytics and learning of financial businesses and data. The comparison, criticism and discussion of classic vs. modern AI techniques for finance are followed. Lastly, open issues and opportunities address future AI-empowered finance and finance-motivated AI research.