The company employs engineers in Seattle on machine–learning technology.

Published online as an accepted paper in the Journal of Clinical Sleep Medicine, the position statement was developed by the AASM's Artificial Intelligence in Sleep Medicine Committee. According to the statement, the electrophysiological data collected during polysomnography -- the most comprehensive type of sleep study -- is well-positioned for enhanced analysis through AI and machine-assisted learning. "When we typically think of AI in sleep medicine, the obvious use case is for the scoring of sleep and associated events," said lead author and committee Chair Dr. Cathy Goldstein, associate professor of sleep medicine and neurology at the University of Michigan. "This would streamline the processes of sleep laboratories and free up sleep technologist time for direct patient care." Because of the vast amounts of data collected by sleep centers, AI and machine learning could advance sleep care, resulting in more accurate diagnoses, prediction of disease and treatment prognosis, characterization of disease subtypes, precision in sleep scoring, and optimization and personalization of sleep treatments.

An AI technique called group analysis, used to detect e-commerce fraud, holds great promise for catching fraud rings sooner rather than later. Insurance fraud scams seem to make the news at least every month, as organized criminals seek to exploit the way insurers reimburse clinics, pharmacies and other providers for their services. What's often shocking is how much money fraudsters can steal from insurers before they're caught. Recently, in a single month, two separate alleged fraud rings based in California were busted for scams that investigators say netted $20 million or more. Clearly, there's a need for fraud detection tools that can spot these frauds in their early stages.

We're building safe Artificial General Intelligence (AGI), and ensuring it leads to a good outcome for humans. We believe that unreasonably great results are best delivered by a highly creative group working in concert. We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. This position is subject to a background check for any convictions directly related to its duties and responsibilities.

We're building safe Artificial General Intelligence (AGI), and ensuring it leads to a good outcome for humans. We believe that unreasonably great results are best delivered by a highly creative group working in concert. We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. This position is subject to a background check for any convictions directly related to its duties and responsibilities.

"We're a world leading artificial intelligence (AI) platform that monitors real time and real-world events and provides all-round risk detection and solutions," Rod Moynihan told Insurance Business. Moynihan is the managing director of Dataminr in Australia and New Zealand, a global real-time information discovery company that is pioneering what it sees as ground-breaking technology for detecting, classifying, and determining the significance of public information in real time. Moynihan recently gave an interview to Insurance Business to explain how the platform works and how it can aid insurers. Using public information and data available from across the world, Dataminr's AI platform finds, dissects and quantifies a large amount of data to make sense of potentially large impact events that can affect customers. "It sorts through millions upon millions of publicly available data," explained Moynihan.

While the generalization properties of neural networks are not yet well understood, several papers argue that wide minima generalize better than narrow minima. In this paper, through detailed experiments that not only corroborate the generalization properties of wide minima, we also provide empirical evidence for a new hypothesis that the density of wide minima is likely lower than the density of narrow minima. Further, motivated by this hypothesis, we design a novel explore-exploit learning rate schedule. On a variety of image and natural language datasets, compared to their original hand-tuned learning rate baselines, we show that our explore-exploit schedule can result in either up to 0.5\% higher absolute accuracy using the original training budget or up to 44\% reduced training time while achieving the original reported accuracy.

The input to the \emph{sets-$k$-means} problem is an integer $k\geq 1$ and a set $\mathcal{P}=\{P_1,\cdots,P_n\}$ of sets in $\mathbb{R}^d$. The goal is to compute a set $C$ of $k$ centers (points) in $\mathbb{R}^d$ that minimizes the sum $\sum_{P\in \mathcal{P}} \min_{p\in P, c\in C}\left\| p-c \right\|^2$ of squared distances to these sets. An \emph{$\varepsilon$-core-set} for this problem is a weighted subset of $\mathcal{P}$ that approximates this sum up to $1\pm\varepsilon$ factor, for \emph{every} set $C$ of $k$ centers in $\mathbb{R}^d$. We prove that such a core-set of $O(\log^2{n})$ sets always exists, and can be computed in $O(n\log{n})$ time, for every input $\mathcal{P}$ and every fixed $d,k\geq 1$ and $\varepsilon \in (0,1)$. The result easily generalized for any metric space, distances to the power of $z>0$, and M-estimators that handle outliers. Applying an inefficient but optimal algorithm on this coreset allows us to obtain the first PTAS ($1+\varepsilon$ approximation) for the sets-$k$-means problem that takes time near linear in $n$. This is the first result even for sets-mean on the plane ($k=1$, $d=2$). Open source code and experimental results for document classification and facility locations are also provided.

This paper proposes a strategy for visual prediction in the context of autonomous driving. Humans, when not distracted or drunk, are still the best drivers you can currently find. For this reason we take inspiration from two theoretical ideas about the human mind and its neural organization. The first idea concerns how the brain uses a hierarchical structure of neuron ensembles to extract abstract concepts from visual experience and code them into compact representations. The second idea suggests that these neural perceptual representations are not neutral but functional to the prediction of the future state of affairs in the environment. Similarly, the prediction mechanism is not neutral but oriented to the current planning of a future action. We identify within the deep learning framework two artificial counterparts of the aforementioned neurocognitive theories. We find a correspondence between the first theoretical idea and the architecture of convolutional autoencoders, while we translate the second theory into a training procedure that learns compact representations which are not neutral but oriented to driving tasks, from two distinct perspectives. From a static perspective, we force groups of neural units in the compact representations to distinctly represent specific concepts crucial to the driving task. From a dynamic perspective, we encourage the compact representations to be predictive of how the current road scenario will change in the future. We successfully learn compact representations that use as few as 16 neural units for each of the two basic driving concepts we consider: car and lane. We prove the efficiency of our proposed perceptual representations on the SYNTHIA dataset. Our source code is available at https://github.com/3lis/rnn_vae

Social media channels, such as Facebook, Twitter, and Instagram, have altered our world forever. People are now increasingly connected than ever and reveal a sort of digital persona. Although social media certainly has several remarkable features, the demerits are undeniable as well. Recent studies have indicated a correlation between high usage of social media sites and increased depression. The present study aims to exploit machine learning techniques for detecting a probable depressed Twitter user based on both, his/her network behavior and tweets. For this purpose, we trained and tested classifiers to distinguish whether a user is depressed or not using features extracted from his/ her activities in the network and tweets. The results showed that the more features are used, the higher are the accuracy and F-measure scores in detecting depressed users. This method is a data-driven, predictive approach for early detection of depression or other mental illnesses. This study's main contribution is the exploration part of the features and its impact on detecting the depression level.