Well-designed diagnostic tasks have played a key role in studying the failure of neural nets (NNs) to generalize systematically. Famous examples include SCAN and Compositional Table Lookup (CTL). Here we introduce CTL++, a new diagnostic dataset based on compositions of unary symbolic functions. While the original CTL is used to test length generalization or productivity, CTL++ is designed to test systematicity of NNs, that is, their capability to generalize to unseen compositions of known functions. CTL++ splits functions into groups and tests performance on group elements composed in a way not seen during training. We show that recent CTL-solving Transformer variants fail on CTL++. The simplicity of the task design allows for fine-grained control of task difficulty, as well as many insightful analyses. For example, we measure how much overlap between groups is needed by tested NNs for learning to compose. We also visualize how learned symbol representations in outputs of functions from different groups are compatible in case of success but not in case of failure. These results provide insights into failure cases reported on more complex compositions in the natural language domain. Our code is public.

The COVID-19 pandemic has affected countries across the world, demanding drastic public health policies to mitigate the spread of infection, leading to economic crisis as a collateral damage. In this work, we investigated the impact of human mobility (described via international commercial flights) on COVID-19 infection dynamics at the global scale. For this, we developed a graph neural network-based framework referred to as Dynamic Connectivity GraphSAGE (DCSAGE), which operates over spatiotemporal graphs and is well-suited for dynamically changing adjacency information. To obtain insights on the relative impact of different geographical locations, due to their associated air traffic, on the evolution of the pandemic, we conducted local sensitivity analysis on our model through node perturbation experiments. From our analyses, we identified Western Europe, North America, and Middle East as the leading geographical locations fueling the pandemic, attributed to the enormity of air traffic originating or transiting through these regions. We used these observations to identify tangible air traffic reduction strategies that can have a high impact on controlling the pandemic, with minimal interference to human mobility. Our work provides a robust deep learning-based tool to study global pandemics and is of key relevance to policy makers to take informed decisions regarding air traffic restrictions during future outbreaks.

Several biomedical language models have already been developed for clinical language inference. However, these models typically utilize general vocabularies and are trained on relatively small clinical corpora. We sought to evaluate the impact of using a domain-specific vocabulary and a large clinical training corpus on the performance of these language models in clinical language inference. We trained a Bidirectional Encoder Decoder from Transformers (BERT) model using a diverse, deidentified corpus of 75 million deidentified clinical notes authored at the University of California, San Francisco (UCSF). We evaluated this model on several clinical language inference benchmark tasks: clinical and temporal concept recognition, relation extraction and medical language inference. We also evaluated our model on two tasks using discharge summaries from UCSF: diagnostic code assignment and therapeutic class inference. Our model performs at par with the best publicly available biomedical language models of comparable sizes on the public benchmark tasks, and is significantly better than these models in a within-system evaluation on the two tasks using UCSF data. The use of in-domain vocabulary appears to improve the encoding of longer documents. The use of large clinical corpora appears to enhance document encoding and inferential accuracy. However, further research is needed to improve abbreviation resolution, and numerical, temporal, and implicitly causal inference.

Rendering to their abilities to provide ubiquitous connectivity, flexibly and cost effectively, unmanned aerial vehicles (UAVs) have been getting more and more research attention. To take the UAVs' performance to the next level, however, they need to be merged with some other technologies like non-orthogonal multiple access (NOMA) and millimeter wave (mmWave), which both promise high spectral efficiency (SE). As managing UAVs efficiently may not be possible using model-based techniques, another key innovative technology that UAVs will inevitably need to leverage is artificial intelligence (AI). Designing an AI-based technique that adaptively allocates radio resources and places UAVs in 3D space to meet certain communication objectives, however, is a tough row to hoe. In this paper, we propose a neuroevolution of augmenting topologies NEAT framework, referred to as ProSky, to manage NOMA-mmWave-UAV networks. ProSky exhibits a remarkable performance improvement over a model-based method. Moreover, ProSky learns 5.3 times faster than and outperforms, in both SE and energy efficiency EE while being reasonably fair, a deep reinforcement learning DRL based scheme. The ProSky source code is accessible to use here: https://github.com/Fouzibenfaid/ProSky

A British humanoid called Ai-Da has made history by becoming the first robot to speak at the House of Lords. Addressing members of the House of Lords Communications and Digital Committee on Tuesday afternoon, the bot spoke about whether creativity is under attack from AI and technology. When asked: 'How do you produce art and how is this different to what human artists produce?', Ai-Da replied: 'I could use my paintings by cameras in my eyes, my AI algorithms and my robotic arm to paint on canvas, which result in visually appealing images. 'For my poetry using neutral networks, this involves analysing a large corpus of text to identify common content and poetic structures, and then using these structures/content to generate new poems. 'How this differs to humans is consciousness.

Silent Eight announced an extension to its existing partnership with HSBC to tackle financial crime. The new service will cover the deployment of Negative News Screening that leverages machine learning to identify individuals who pose a greater risk for money laundering, fraud or terrorist financing. As financial crime continues to present a challenge, banks need to pivot to an increased use of Machine Learning within compliance, and move away from manual processes or alert scoring. Silent Eights' solution provides a more effective approach to address true matches and resolve the issue of false identifications. With this expansion, Silent Eight will be solving name screening matches across every risk type within HSBC.

Our Women in Robotics list turns 10 this year and we are delighted to introduce you to another amazing "50 women in robotics you need to know about" as we also celebrate Ada Lovelace Day. We have now profiled more than 300 women AND non-binary people making important contributions to robotics since the list began in 2013. This year our 50 come from robotics companies (small and large), self-driving car companies, governments, research organizations and the media. The list covers the globe, with the chosen ones having nationalities from the EU, UK, USA, Australia, China, Turkey, India and Kenya. A number of women come from influential companies that are household names such as NASA, ABB, GE, Toyota and the Wall Street Journal.

Since photovoltaic (PV) plants require periodic maintenance, using Unmanned Aerial Vehicles (UAV) for inspections can help reduce costs. The thermal and visual inspection of PV installations is currently based on UAV photogrammetry. A UAV equipped with a Global Positioning System (GPS) receiver is assigned a flight zone: the UAV will cover it back and forth to collect images to be later composed in an orthomosaic. The UAV typically flies at a height above the ground that is appropriate to ensure that images overlap even in the presence of GPS positioning errors. However, this approach has two limitations. Firstly, it requires to cover the whole flight zone, including "empty" areas between PV module rows. Secondly, flying high above the ground limits the resolution of the images to be later inspected. The article proposes a novel approach using an autonomous UAV equipped with an RGB and a thermal camera for PV module tracking. The UAV moves along PV module rows at a lower height than usual and inspects them back and forth in a boustrophedon way by ignoring "empty" areas with no PV modules. Experimental tests performed in simulation and an actual PV plant are reported.

Discriminative pre-trained language models (PrLMs) can be generalized as denoising auto-encoders that work with two procedures, ennoising and denoising. First, an ennoising process corrupts texts with arbitrary noising functions to construct training instances. Then, a denoising language model is trained to restore the corrupted tokens. Existing studies have made progress by optimizing independent strategies of either ennoising or denosing. They treat training instances equally throughout the training process, with little attention on the individual contribution of those instances. To model explicit signals of instance contribution, this work proposes to estimate the complexity of restoring the original sentences from corrupted ones in language model pre-training. The estimations involve the corruption degree in the ennoising data construction process and the prediction confidence in the denoising counterpart. Experimental results on natural language understanding and reading comprehension benchmarks show that our approach improves pre-training efficiency, effectiveness, and robustness. Code is publicly available at https://github.com/cooelf/InstanceReg

IceCube, a cubic-kilometer array of optical sensors built to detect atmospheric and astrophysical neutrinos between 1 GeV and 1 PeV, is deployed 1.45 km to 2.45 km below the surface of the ice sheet at the South Pole. The classification and reconstruction of events from the in-ice detectors play a central role in the analysis of data from IceCube. Reconstructing and classifying events is a challenge due to the irregular detector geometry, inhomogeneous scattering and absorption of light in the ice and, below 100 GeV, the relatively low number of signal photons produced per event. To address this challenge, it is possible to represent IceCube events as point cloud graphs and use a Graph Neural Network (GNN) as the classification and reconstruction method. The GNN is capable of distinguishing neutrino events from cosmic-ray backgrounds, classifying different neutrino event types, and reconstructing the deposited energy, direction and interaction vertex. Based on simulation, we provide a comparison in the 1-100 GeV energy range to the current state-of-the-art maximum likelihood techniques used in current IceCube analyses, including the effects of known systematic uncertainties. For neutrino event classification, the GNN increases the signal efficiency by 18% at a fixed false positive rate (FPR), compared to current IceCube methods. Alternatively, the GNN offers a reduction of the FPR by over a factor 8 (to below half a percent) at a fixed signal efficiency. For the reconstruction of energy, direction, and interaction vertex, the resolution improves by an average of 13%-20% compared to current maximum likelihood techniques in the energy range of 1-30 GeV. The GNN, when run on a GPU, is capable of processing IceCube events at a rate nearly double of the median IceCube trigger rate of 2.7 kHz, which opens the possibility of using low energy neutrinos in online searches for transient events.