Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering. In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to train embeddings to discriminate an unprecedented O(40M) ultra-fine-grained semantic labels. Graph-RISE outperforms state-of-the-art image embedding algorithms on several evaluation tasks, including image classification and triplet ranking. We provide case studies to demonstrate that, qualitatively, image retrieval based on Graph-RISE effectively captures semantics and, compared to the state-of-the-art, differentiates nuances at levels that are closer to human-perception.

Rational decision making in its linguistic description means making logical decisions. In essence, a rational agent optimally processes all relevant information to achieve its goal. Rationality has two elements and these are the use of relevant information and the efficient processing of such information. In reality, relevant information is incomplete, imperfect and the processing engine, which is a brain for humans, is suboptimal. Humans are risk averse rather than utility maximizers. In the real world, problems are predominantly non-convex and this makes the idea of rational decision-making fundamentally unachievable and Herbert Simon called this bounded rationality. There is a trade-off between the amount of information used for decision-making and the complexity of the decision model used. This explores whether machine rationality is subjective and concludes that indeed it is.

This paper considers the perturbed stochastic gradient descent algorithm and shows that it finds $\epsilon$-second order stationary points ($\left\|\nabla f(x)\right\|\leq \epsilon$ and $\nabla^2 f(x) \succeq -\sqrt{\epsilon} \mathbf{I}$) in $\tilde{O}(d/\epsilon^4)$ iterations, giving the first result that has linear dependence on dimension for this setting. For the special case, where stochastic gradients are Lipschitz, the dependence on dimension reduces to polylogarithmic. In addition to giving new results, this paper also presents a simplified proof strategy that gives a shorter and more elegant proof of previously known results (Jin et al. 2017) on perturbed gradient descent algorithm.

Artificial Intelligence (AI) is necessary to address the large and growing deficit in retina and healthcare access globally. And mobile AI diagnostic platforms running in the Cloud may effectively and efficiently distribute such AI capability. Here we sought to evaluate the feasibility of Cloud-based mobile artificial intelligence for detection of retinal disease. And to evaluate the accuracy of a particular such system for detection of subretinal fluid (SRF) and macula edema (ME) on OCT scans. A multicenter retrospective image analysis was conducted in which board-certified ophthalmologists with fellowship training in retina evaluated OCT images of the macula. They noted the presence or absence of ME or SRF, then compared their assessment to that obtained from Fluid Intelligence, a mobile AI app that detects SRF and ME on OCT scans. Investigators consecutively selected retinal OCTs, while making effort to balance the number of scans with retinal fluid and scans without. Exclusion criteria included poor scan quality, ambiguous features, macula holes, retinoschisis, and dense epiretinal membranes. Accuracy in the form of sensitivity and specificity of the AI mobile App was determined by comparing its assessments to those of the retina specialists. At the time of this submission, five centers have completed their initial studies. This consists of a total of 283 OCT scans of which 155 had either ME or SRF ("wet") and 128 did not ("dry"). The sensitivity ranged from 82.5% to 97% with a weighted average of 89.3%. The specificity ranged from 52% to 100% with a weighted average of 81.23%. CONCLUSION: Cloud-based Mobile AI technology is feasible for the detection retinal disease. In particular, Fluid Intelligence (alpha version), is sufficiently accurate as a screening tool for SRF and ME, especially in underserved areas. Further studies and technology development is needed.

Abstract--Cardiovascular disease (CVD) is the global leading cause of death. A strong risk factor for CVD events is the amount of coronary artery calcium (CAC). To meet demands of the increasing interest in quantification of CAC, i.e. coronary calcium scoring,especially as an unrequested finding for screening and research, automatic methods have been proposed. Current automatic calcium scoring methods are relatively computationally expensive and only provide scores for one type of CT. To address this, we propose a computationally efficient method that employs two ConvNets: the first performs registration to align the fields of view of input CTs and the second performs direct regression of the calcium score, thereby circumventing timeconsuming intermediateCAC segmentation. Optional decision feedback provides insight in the regions that contributed to the calcium score. Experiments were performed using 903 cardiac CT and 1,687 chest CT scans. The method predicted calcium scores in less than 0.3 s. Intra-class correlation coefficient between predicted and manual calcium scores was 0.98 for both cardiac and chest CT. The method showed almost perfect agreement between automatic and manual CVD risk categorization in both datasets, with a linearly weighted Cohen's kappa of 0.95 in cardiac CT and 0.93 in chest CT. Performance is similar to that of state-of-the-art methods, but the proposed method is hundreds of times faster. By providing visual feedback, insight is given in the decision process, making it readily implementable in clinical and research settings. I. INTRODUCTION Cardiovascular disease (CVD) is the global leading cause of death [1]. To reduce the burden of cardiovascular disease the World Health Organization underlines the need for early detection and treatment of individuals with CVD or those who are at high cardiovascular risk due to the presence of one or more risk factors [2]. Quantification of CAC, i.e. calcium scoring, is typically performed in dedicated Personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending a request to pubs-permissions@ieee.org. Bob D. de Vos, Jelmer M. Wolterink, Nikolas Lessmann, and Ivana Išgum are with the Image Sciences Institute of the University Medical Center Utrecht and Utrecht University, Utrecht, The Netherlands.

Abstract--In this paper we consider the task of detecting abnormal communication volume occurring at node-level in communication networks. The signal of the communication activity is modeled by means of a clique stream: each occurring communication event is instantaneous and activates an undirected subgraph spanning over a set of equally participating nodes. We present a probabilistic framework to model and assess the communication volume observed at any single node. Specifically, we employ nonparametric regression to learn the probability that a node takes part in a certain event knowing the set of other nodes that are involved. On the top of that, we present a concentration inequality around the estimated volume of events in which a node could participate, which in turn allows us to build an efficient and interpretable anomaly scoring function. Finally, the superior performance of the proposed approach is empirically demonstrated in real-world sensor network data, as well as using synthetic communication activity that is in accordance with that latter setting. I. INTRODUCTION Monitoring the activity in communication networks has become a popular area of research and particular attention has been paid to detection tasks such as spotting events or anomalies. Aneffective way to represent the communication activity is via a dynamic graph where the entities are considered to be nodes, and each communication event (or more simply event) to be represented by a set of connecting edges that appear at a specific time interval.

Nobody knows who she was, just that she was different: a teenage girl from over 50,000 years ago of such strange uniqueness she looked to be a'hybrid' ancestor to modern humans that scientists had never seen before. Only now, researchers have uncovered evidence she wasn't alone. In a new study analysing the complex mess of humanity's prehistory, scientists have used artificial intelligence (AI) to identify an unknown human ancestor species that modern humans encountered – and shared dalliances with – on the long trek out of Africa millennia ago. "About 80,000 years ago, the so-called Out of Africa occurred, when part of the human population, which already consisted of modern humans, abandoned the African continent and migrated to other continents, giving rise to all the current populations", explains evolutionary biologist Jaume Bertranpetit from the Universitat Pompeu Fabra in Spain. As modern humans forged this path into the landmass of Eurasia, they forged some other things too – breeding with ancient and extinct hominids from other species.

Whether you are working on predicting data in an office setting or just competing in a Kaggle competition, it's important to test out different models to find the best fit for the data you are working with. I recently had the opportunity to compete with some very smart colleagues in a private Kaggle competition predicting faulty water pumps in Tanzania. I ran the following models after doing some data cleaning and I'll show you the results. First, we need to take a look at the data we're working with. In this particular data set, the features were in a separate file than the labels.

Real-life mobile phone data may contain noisy instances, which is a fundamental issue for building a prediction model with many potential negative consequences. The complexity of the inferred model may increase, may arise overfitting problem, and thereby the overall prediction accuracy of the model may decrease. In this paper, we address these issues and present a robust prediction model for real-life mobile phone data of individual users, in order to improve the prediction accuracy of the model. In our robust model, we first effectively identify and eliminate the noisy instances from the training dataset by determining a dynamic noise threshold using naive Bayes classifier and laplace estimator, which may differ from user-to-user according to their unique behavioral patterns. After that, we employ the most popular rule-based machine learning classification technique, i.e., decision tree, on the noise-free quality dataset to build the prediction model. Experimental results on the real-life mobile phone datasets (e.g., phone call log) of individual mobile phone users, show the effectiveness of our robust model in terms of precision, recall and f-measure.

One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids learning dependencies beyond the truncation horizon. In contrast, the online training algorithm Real Time Recurrent Learning (RTRL) provides untruncated gradients, with the disadvantage of impractically large computational costs. Recently published approaches reduce these costs by providing noisy approximations of RTRL. We present a new approximation algorithm of RTRL, Optimal Kronecker-Sum Approximation (OK). We prove that OK is optimal for a class of approximations of RTRL, which includes all approaches published so far. Additionally, we show that OK has empirically negligible noise: Unlike previous algorithms it matches TBPTT in a real world task (character-level Penn TreeBank) and can exploit online parameter updates to outperform TBPTT in a synthetic string memorization task.