Graph Convolutional Networks (GCNs) have gained significant developments in representation learning on graphs. However, current GCNs suffer from two common challenges: 1) GCNs are only effective with shallow structures; stacking multiple GCN layers will lead to over-smoothing. 2) GCNs do not scale well with large, dense graphs due to the recursive neighborhood expansion. We generalize the propagation strategies of current GCNs as a \emph{"Sink$\to$Source"} mode, which seems to be an underlying cause of the two challenges. To address these issues intrinsically, in this paper, we study the information propagation mechanism in a \emph{"Source$\to$Sink"} mode. We introduce a new concept "information flow path" that explicitly defines where information originates and how it diffuses. Then a novel framework, namely Flow Graph Network (FlowGN), is proposed to learn node representations. FlowGN is computationally efficient and flexible in propagation strategies. Moreover, FlowGN decouples the layer structure from the information propagation process, removing the interior constraint of applying deep structures in traditional GCNs. Further experiments on public datasets demonstrate the superiority of FlowGN against state-of-the-art GCNs.

The modern world is changing more and more quickly with each passing year. If you don't pay attention to new changes or keep up the pace, it's easy to fall behind the times (and the market) while other companies beat you to the punch. To keep abreast of current changes – at least at a level of basic understanding. Adding to that, if you can't understand the buzzwords others are using in conversation, it's much harder to look smart while participating in that conversation. In this post, we're going to give you the 10 IT & technology buzzwords you won't be able to avoid in 2020 so that you can stay poised to take advantage of market opportunities and new conversations alike. The first in our definitive rundown of tech buzzwords 2020 is computer vision. Exciting and futuristic, the concept of computer vision is based on computing devices or programs gaining the ability to extract detailed information from visual images. In a computing context, 'vision' involves systems that can identify items, places, objects, or even humans from visuals mediums – images caught by a camera or sensor.

Singapore's Health Sciences Authority has approved the use of an artificial intelligence-powered (AI) software for the automated analysis and reporting of vascular ultrasound scans. Developed by See-Mode Technologies, the application taps deep learning, text recognition, and signal processing technologies with the aim of helping clinicians interpret such images -- a task that typically is performed manually, time-consuming, and error-prone. Such scans, used for patients with cardiovascular or heart diseases, are commonly analysed by a sonographer or radiologist who has to manually review between 50 and 150 images for each patient, according to See-Mode. No system is infallible and cybersecurity breaches are inevitable, but Singapore needs to do better in mitigating the risks and following through on its pledge to safeguard citizen data. "The end result is a hand-written, paper-based template filled with drawings, numbers, and measurements, which can take as long as 20 minutes per patient for severe cases," it said in a statement Tuesday.

Key Questions Answered in this Report: • What is the estimated global artificial intelligence in agriculture market size in terms of value during the period 2018-2024? Global Artificial Intelligence (AI) in Agriculture Market Forecast, 2019-2024 The Global Artificial Intelligence (AI) in Agriculture Market Analysis projects the market to grow at a significant CAGR of 28.38% during the forecast period from 2019 to 2024. The reported growth in the market is expected to be driven by the increasing need to optimize farm operation planning, growing demand to derive insights from emerging complexities of data-driven farming, and rising development of autonomous equipment in agriculture. Artificial intelligence has emerged to be a strong driving force behind the growth of data-driven farming.Regions and countries where agriculture is the major source of livelihood and sustenance, the artificial intelligence technology has led to greater profitability in the farms of those economies. The reduction in expenditure and resultant positive RoI with AI's integration in farm equipment and operations has even reached above 30% in a few countries.

Artificial intelligence is here, and it's being put to work across all manner of industries and applications. While the technology still has someway to go before we see machines capable of true independent thought and decision-making, what we do have is sending waves through the business world. While only 23 percent of businesses have incorporated the technology into the products and services they offer right now, a massive 83 percent have named AI as a strategic priority for the near future. Global spending on cognitive and AI systems is estimated to reach $57.6 billion in 2021 and the AI market is set to grow to become a $190 billion industry by 2025. What are the benefits of AI to businesses according to industry experts?

One sector that is expected to boom over the next decade is artificial intelligence. There are many businesses that claim they're part of AI development, so it's hard to know which shares will give the clearest exposure to AI and deliver good returns. All of the top US businesses are doing something with AI one way or another. Microsoft, Alphabet (Google), Facebook, Amazon and Apple are all trying to make their technology better with AI. If it's hard to pick one winner out of a group then why not just buy the whole group?

Research has found that many occupational accidents are foreseeable, being the result of people's unsafe behaviour from a retrospective point of view. The prediction of workers' safety behaviour will enable the prior insights into each worker's behavioural tendency and will be useful in the design of management practices prior to the occurrence of accidents and contribute to the reduction of injury rates. In recent years, researchers have found that people do have stable predispositions to engage in certain safety behavioural patterns which vary among individuals as a function of personality features. In this study, an innovative forecasting model, which employs machine learning algorithms, is developed to estimate construction workers' behavioural tendency based on the Big Five personality taxonomy. The data-driven nature of machine learning technique enabled a reliable estimate of the personality-safety behaviour relationship, which allowed this study to provide novel insight that nonlinearity may exist in the relationship between construction workers' personality traits and safety behaviour. The developed model is found to be sufficient to have satisfactory accuracy in explaining and predicting workers' safety behaviour. This finding provides the empirical evidence to support the usefulness of personality traits as effective predictors of people's safety behaviour at work. In addition, this study could have practical implications. The machine learning model developed can help identify vulnerable workers who are more prone to undertake unsafe behaviours, which is proven to have good prediction accuracy and is thereby potentially useful for decision making and safety management on construction sites.

Motivation: Untargeted metabolomics comprehensively characterizes small molecules and elucidates activities of biochemical pathways within a biological sample. Despite computational advances, interpreting collected measurements and determining their biological role remains a challenge. Results: To interpret measurements, we present an inference-based approach, termed Probabilistic modeling for Untargeted Metabolomics Analysis (PUMA). Our approach captures measurements and known information about the sample under study in a generative model and uses stochastic sampling to compute posterior probability distributions. PUMA predicts the likelihood of pathways being active, and then derives a probabilistic annotation, which assigns chemical identities to the measurements. PUMA is validated on synthetic datasets. When applied to test cases, the resulting pathway activities are biologically meaningful and distinctly different from those obtained using statistical pathway enrichment techniques. Annotation results are in agreement to those obtained using other tools that utilize additional information in the form of spectral signatures. Importantly, PUMA annotates many additional measurements.

In mixed multi-view data, multiple sets of diverse features are measured on the same set of samples. By integrating all available data sources, we seek to discover common group structure among the samples that may be hidden in individualistic cluster analyses of a single data-view. While several techniques for such integrative clustering have been explored, we propose and develop a convex formalization that will inherit the strong statistical, mathematical and empirical properties of increasingly popular convex clustering methods. Specifically, our Integrative Generalized Convex Clustering Optimization (iGecco) method employs different convex distances, losses, or divergences for each of the different data views with a joint convex fusion penalty that leads to common groups. Additionally, integrating mixed multi-view data is often challenging when each data source is high-dimensional. To perform feature selection in such scenarios, we develop an adaptive shifted group-lasso penalty that selects features by shrinking them towards their loss-specific centers. Our so-called iGecco+ approach selects features from each data-view that are best for determining the groups, often leading to improved integrative clustering. To fit our model, we develop a new type of generalized multi-block ADMM algorithm using sub-problem approximations that more efficiently fits our model for big data sets. Through a series of numerical experiments and real data examples on text mining and genomics, we show that iGecco+ achieves superior empirical performance for high-dimensional mixed multi-view data.

Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stochastic policies for exploration through action space. However, this does not ensure exploration in the state space. In this work, we instead consider the distribution of discounted weighting of states, and propose to maximize the entropy of a lower bound approximation to the weighting of a state, based on latent space state representation. We propose entropy regularization based on the marginal state distribution, to encourage the policy to have a more uniform distribution over the state space for exploration. Our approach based on marginal state distribution achieves superior state space coverage on complex gridworld domains, that translate into empirical gains in sparse reward 3D maze navigation and continuous control domains compared to entropy regularization with stochastic policies.