Community detection methods attempt to divide a network into groups of nodes that share similar properties, thus revealing its large-scale structure. A major challenge when employing such methods is that they are often degenerate, typically yielding a complex landscape of competing answers. As an attempt to extract understanding from a population of alternative solutions, many methods exist to establish a consensus among them in the form of a single partition "point estimate" that summarizes the whole distribution. Here we show that it is in general not possible to obtain a consistent answer from such point estimates when the underlying distribution is too heterogeneous. As an alternative, we provide a comprehensive set of methods designed to characterize and summarize complex populations of partitions in a manner that captures not only the existing consensus, but also the dissensus between elements of the population. Our approach is able to model mixed populations of partitions where multiple consensuses can coexist, representing different competing hypotheses for the network structure. We also show how our methods can be used to compare pairs of partitions, how they can be generalized to hierarchical divisions, and be used to perform statistical model selection between competing hypotheses.

Deep neural networks are generally designed as a stack of differentiable layers, in which a prediction is obtained only after running the full stack. Recently, some contributions have proposed techniques to endow the networks with early exits, allowing to obtain predictions at intermediate points of the stack. These multi-output networks have a number of advantages, including: (i) significant reductions of the inference time, (ii) reduced tendency to overfitting and vanishing gradients, and (iii) capability of being distributed over multi-tier computation platforms. In addition, they connect to the wider themes of biological plausibility and layered cognitive reasoning. In this paper, we provide a comprehensive introduction to this family of neural networks, by describing in a unified fashion the way these architectures can be designed, trained, and actually deployed in time-constrained scenarios. We also describe in-depth their application scenarios in 5G and Fog computing environments, as long as some of the open research questions connected to them.

Toxic man-made mercury pollution has been discovered in the deepest part of the ocean, in the Marianas Trench -- more than six miles below the surface. Researchers from China and the US used submarine robots to identify mercury in the fish and crustaceans living in the deepest part of the western Pacific Ocean. Mercury enters the atmosphere through the burning of fossil fuels, mining and manufacturing. It can then be transported into the oceans via rainfall. The liquid metal -- which was once used in thermometers before being banned -- is highly toxic and can be ingested via polluted seafood.

A new tech startup has announced plans to hold a flying car race in Australia before the end of 2020, the first of what it hopes will be a series of events that could become the 21st century version of F1. Organized by Airspeeder, a tech startup with offices in Adelaide and London, the race will feature two remotely piloted flying cars, racing through the outskirts of Coober Pedy, a small town in the Australian Outback used as the setting for the original Mad Max films. The first race is planned as a public exhibition, with support from Australia's Civil Aviation Safety Authority, and Airspeeder hopes it will be the first of an international circuit of races that could expand to include piloted vehicles. 'Le Mans, Bathurst, Monaco, there are these amazing places where we've seen the birth of new sports,' Airspeeder's Matt Pearson told ABC News. 'This is such a great place for us to basically create that next iconic place for racing.'

Google Maps is working on a new feature that will show you how to reach the nearest public transport connection, according to new leaked screenshots. The new Maps filter will let users choose what mode of transportation they will be using at the very beginning of their daily commute, the screenshots show. Once rolled out, the feature will allow commuters to work out their preferred route to various transport connections, such as the train station, when they return to the workplace after the coronavirus pandemic. The screenshots also reveal an option to get more accurate Uber fares using data from Google Maps and a slightly new design for the Maps interface. 'Google Maps is working on route options with "Connections to Public Transit", such as car and transit, bicycle and transit, auto rickshaw, ride service [and] motorcycle and transit,' said Jane Wong, a Hong Kong-based hacker, tech blogger and software engineer, who leaked the screenshots.

A personalised cancer vaccine designed to boost the body's own natural defences when used alongside chemotherapy shows'promising signs' after a clinical trial. The treatment is created by taking a biopsy of a tumour and then using artificial intelligence to identify certain proteins not recognised by the immune system. They use these proteins to create tailor-made vaccines for each individual cancer patients and then administer them alongside immunotherapy drug atezolizumab. So far researchers have only tested it on patients with advanced cancers and just 8 per cent saw their tumours shrink - with 49 per cent seeing no change. An international team of researchers found the treatment, known as RO7198457, was'well tolerated' by patients and the they experienced'low-to-moderate' side effects. This is early days in the development of the treatment as the clinical trials were only designed to test its safety, further testing is needed to see how effective it is.

Two models based on convolutional neural networks are trained to predict the two-dimensional velocity-fluctuation fields at different wall-normal locations in a turbulent open channel flow, using the wall-shear-stress components and the wall pressure as inputs. The first model is a fully-convolutional neural network (FCN) which directly predicts the fluctuations, while the second one reconstructs the flow fields using a linear combination of orthonormal basis functions, obtained through proper orthogonal decomposition (POD), hence named FCN-POD. Both models are trained using data from two direct numerical simulations (DNS) at friction Reynolds numbers $Re_{\tau} = 180$ and $550$. Thanks to their ability to predict the nonlinear interactions in the flow, both models show a better prediction performance than the extended proper orthogonal decomposition (EPOD), which establishes a linear relation between input and output fields. The performance of the various models is compared based on predictions of the instantaneous fluctuation fields, turbulence statistics and power-spectral densities. The FCN exhibits the best predictions closer to the wall, whereas the FCN-POD model provides better predictions at larger wall-normal distances. We also assessed the feasibility of performing transfer learning for the FCN model, using the weights from $Re_{\tau}=180$ to initialize those of the $Re_{\tau}=550$ case. Our results indicate that it is possible to obtain a performance similar to that of the reference model up to $y^{+}=50$, with $50\%$ and $25\%$ of the original training data. These non-intrusive sensing models will play an important role in applications related to closed-loop control of wall-bounded turbulence.

We introduce Neural Dynamical Systems (NDS), a method of learning dynamical models in various gray-box settings which incorporates prior knowledge in the form of systems of ordinary differential equations. NDS uses neural networks to estimate free parameters of the system, predicts residual terms, and numerically integrates over time to predict future states. A key insight is that many real dynamic systems of interest are hard to model because the dynamics may vary across rollouts. We mitigate this problem by taking a trajectory of prior states as the input to NDS and train it to re-estimate system parameters using the preceding trajectory. We find that NDS learns dynamics with higher accuracy and fewer samples than a variety of deep learning methods that do not incorporate the prior knowledge and methods from the system identification literature which do. We demonstrate these advantages first on synthetic dynamical systems and then on real data captured from deuterium shots from a nuclear fusion reactor.

A key challenge for reinforcement learning (RL) consists of learning in environments with sparse extrinsic rewards. In contrast to current RL methods, humans are able to learn new skills with little or no reward by using various forms of intrinsic motivation. We propose AMIGo, a novel agent incorporating a goal-generating teacher that proposes Adversarially Motivated Intrinsic Goals to train a goal-conditioned "student" policy in the absence of (or alongside) environment reward. Specifically, through a simple but effective "constructively adversarial" objective, the teacher learns to propose increasingly challenging---yet achievable---goals that allow the student to learn general skills for acting in a new environment, independent of the task to be solved. We show that our method generates a natural curriculum of self-proposed goals which ultimately allows the agent to solve challenging procedurally-generated tasks where other forms of intrinsic motivation and state-of-the-art RL methods fail.

Knowledge Graph Completion (KGC) has been proposed to improve Knowledge Graphs by filling in missing connections via link prediction or relation extraction. One of the main difficulties for KGC is a low resource problem. Previous approaches assume sufficient training triples to learn versatile vectors for entities and relations, or a satisfactory number of labeled sentences to train a competent relation extraction model. However, low resource relations are very common in KGs, and those newly added relations often do not have many known samples for training. In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. We propose a general framework called Weighted Relation Adversarial Network, which utilizes an adversarial procedure to help adapt knowledge/features learned from high resource relations to different but related low resource relations. Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations. Experimental results show that the proposed approach outperforms previous methods regarding low resource settings for both link prediction and relation extraction.