Deep learning (DL) neural networks have only recently been employed to interpret chest radiography (CXR) to screen and triage people for pulmonary tuberculosis (TB). No published studies have compared multiple DL systems and populations. We conducted a retrospective evaluation of three DL systems (CAD4TB, Lunit INSIGHT, and qXR) for detecting TB-associated abnormalities in chest radiographs from outpatients in Nepal and Cameroon. All 1196 individuals received a Xpert MTB/RIF assay and a CXR read by two groups of radiologists and the DL systems. Xpert was used as the reference standard.

Classical results on the statistical complexity of linear models have commonly identified the norm of the weights $\|w\|$ as a fundamental capacity measure. Generalizations of this measure to the setting of deep networks have been varied, though a frequently identified quantity is the product of weight norms of each layer. In this work, we show that for a large class of networks possessing a positive homogeneity property, similar bounds may be obtained instead in terms of the norm of the product of weights. Our proof technique generalizes a recently proposed sampling argument, which allows us to demonstrate the existence of sparse approximants of positive homogeneous networks. This yields covering number bounds, which can be converted to generalization bounds for multi-class classification that are comparable to, and in certain cases improve upon, existing results in the literature. Finally, we investigate our sampling procedure empirically, which yields results consistent with our theory.

Matching two sets of items, called set-to-set matching problem, is being recently raised. The difficulties of set-to-set matching over ordinary data matching lie in the exchangeability in 1) set-feature extraction and 2) set-matching score; the pair of sets and the items in each set should be exchangeable. In this paper, we propose a deep learning architecture for the set-to-set matching that overcomes the above difficulties, including two novel modules: 1) a cross-set transformation and 2) cross-similarity function. The former provides the exchangeable set-feature through interactions between two sets in intermediate layers, and the latter provides the exchangeable set matching through calculating the cross-feature similarity of items between two sets. We evaluate the methods through experiments with two industrial applications, fashion set recommendation, and group re-identification. Through these experiments, we show that the proposed methods perform better than a baseline given by an extension of the Set Transformer, the state-of-the-art set-input function.

Graphs and networks are a standard model for describing data or systems based on pairwise interactions. Oftentimes, the underlying relationships involve more than two entities at a time, and hypergraphs are a more faithful model. However, we have fewer rigorous methods that can provide insight from such representations. Here, we develop a computational framework for the problem of clustering hypergraphs with categorical edge labels --- or different interaction types --- where clusters corresponds to groups of nodes that frequently participate in the same type of interaction. Our methodology is based on a combinatorial objective function that is related to correlation clustering but enables the design of much more efficient algorithms. When there are only two label types, our objective can be optimized in polynomial time, using an algorithm based on minimum cuts. Minimizing our objective becomes NP-hard with more than two label types, but we develop fast approximation algorithms based on linear programming relaxations that have theoretical cluster quality guarantees. We demonstrate the efficacy of our algorithms and the scope of the model through problems in edge-label community detection, clustering with temporal data, and exploratory data analysis.

A BSTRACT Since deep neural networks are over-parametrized, they may memorize noisy examples. We address such memorizing issue under the existence of annotation noise. From the fact that deep neural networks cannot generalize neighborhoods of the features acquired via memorization, we find that noisy examples do not consistently incur small losses on the network in the presence of perturbation. Based on this, we propose a novel training method called Learning with Ensemble Consensus (LEC) whose goal is to prevent overfitting noisy examples by eliminating them identified via consensus of an ensemble of perturbed networks. One of the proposed LECs, L TEC outperforms the current state-of-the-art methods on MNIST, CIFAR-10, and CIFAR-100 despite its efficient memory usage. 1 I NTRODUCTION Deep neural networks (DNNs) have shown excellent performance (Krizhevsky et al., 2012; He et al., 2016) on visual recognition datasets (Deng et al., 2009). However, it is difficult to obtain annotated datasets of such high quality in practice (Wang et al., 2018a). Even worse, DNNs may not generalize training data in the presence of noisy examples (Zhang et al., 2016). Therefore, there is an increasing demand for robust training methods. In general, DNNs trained on noisy datasets first generalize clean examples (Arpit et al., 2017).

The potential for machine learning to disrupt the medical profession is the subject of ongoing debate within biomedical informatics. This study aimed to explore psychiatrists' opinions about the potential impact of innovations in artificial intelligence and machine learning on psychiatric practice. In Spring 2019, we conducted a web-based survey of 791 psychiatrists from 22 countries worldwide. The survey measured opinions about the likelihood future technology would fully replace physicians in performing ten key psychiatric tasks. This study involved qualitative descriptive analysis of written response to three open-ended questions in the survey. Comments were classified into four major categories in relation to the impact of future technology on patient-psychiatric interactions, the quality of patient medical care, the profession of psychiatry, and health systems. Overwhelmingly, psychiatrists were skeptical that technology could fully replace human empathy. Many predicted that 'man and machine' would increasingly collaborate in undertaking clinical decisions, with mixed opinions about the benefits and harms of such an arrangement. Participants were optimistic that technology might improve efficiencies and access to care, and reduce costs. Ethical and regulatory considerations received limited attention. This study presents timely information of psychiatrists' view about the scope of artificial intelligence and machine learning on psychiatric practice. Psychiatrists expressed divergent views about the value and impact of future technology with worrying omissions about practice guidelines, and ethical and regulatory issues.

As it becomes easier for humans to do the mundane with the advent of artificial intelligence (AI), the ability of human kind to process complex emotions will become imperative. While the evolution of AI and machine learning--and how they will change our lifestyle, the markets and workforce in many sectors--has been staring in our face, it is important to know the following facts. In the last decade, data and analytics have turned baseball into a bonanza of home runs and strikeouts, basketball became a game won or lost behind the arc and even prompted football coaches to start going for it on fourth down. Microsoft's belief that artificial intelligence (AI) will continue to become relevant in the coming years has often been indicated through moves the tech giant has made in the recent past. Earlier this month, the firm partnered up with Novartis to transform the field of medicine using AI.

Every year, municipalities across South Africa lose millions of Rands from electricity theft. My work as an electrical engineer at Aurecon has led me to think deeply about coming up with ways to not only help solve this problem but consider possible preventative measures that could be put into place. Municipalities generate an enormous amount of data related to electricity distribution and consumption. When combined with real-time data analysis and machine learning algorithms, this information can be used to pick up on electricity theft at any node in the grid. As part of my Research interests, I started to create an algorithm that uses machine learning and artificial neural intelligence to detect electricity theft as well as cable theft, together with one of the Junior Electrical Engineers Tendai Matiza.

Trilobites of the species Ampx priscus were caught in an avalanche of sediment 480 million years ago as they marched in a single-file line on the seafloor of what is now Morocco. The trilobites go marching one by one, hurrah, hurrah … well, at least they did, some 480 million years ago. New fossils from Morocco show lines of trilobites in orderly queues, likely buried by a storm as they trekked from one place to another under the Ordovician seas in an ancient game of "follow the leader." "I think people think that collective behavior is something new in the course of evolution, but actually sophisticated behavior started very, very early," said study leader Jean Vannier, a paleontologist at the University of Lyon in France. Vannier and colleagues from Marrakech, Morocco, discovered the trilobites in the southern part of Morocco in an area known for well-preserved fossils of animals from the early Ordovician, a geologic period that began about 485 million years ago and is one of six periods that make up the Paleozoic era.

If you look at the past four years we've been enjoying substantial economic growth, in order for the economy to be resilient to external shocks we have to continue to diversify and explore new niches to sustain our economic growth. So for this reason we have delved into niche economic areas. We started 2 years ago with Blockchain and we've been attracting significant investment to our island, not only in terms of crypto but also in other areas of technological developments. Now we're seeing new development in companies that are investing in technology and coming here to work and operate from Malta. We're also seeing a spill-over effect, such as companies from the iGaming industry who are producing new products supported by blockchain technology.