The words "fly like an eagle" are famously part of a song, but they may also be words that make some scientists scratch their heads. Especially when it comes to soaring birds like eagles, falcons and hawks, who seem to ascend to great heights over hills, canyons and mountain tops with ease. Scientists realize that upward currents of warm air assist the birds in their flight, but they don't know how the birds find and navigate these thermal plumes. To figure it out, researchers from the University of California San Diego used reinforcement learning to train gliders to autonomously navigate atmospheric thermals, soaring to heights of 700 meters--nearly 2,300 feet. The novel research results, published in the Sept. 19 issue of Nature, highlight the role of vertical wind accelerations and roll-wise torques as viable biological cues for soaring birds.
Birds don't always flap their wings to fly; sometimes they soar by taking advantage of rising columns of warm air known as thermals. With large wingspans, they can stay aloft for hours while expending minimal energy. Exactly how they do it -- navigating tiny changes in unpredictable air currents -- isn't well-known. But scientists are now using artificial intelligence to learn their tricks, and hopefully, they can teach our aircraft to do the same. As described in a paper published this week in the journal Nature, researchers from universities in the US and Italy used machine learning to train an algorithm to control a glider to navigate thermals.
Pricing science is the application of analytical techniques and methods to solve the problem of setting prices. This discipline had its origins in the development of yield management in the airline industry in the 1980s, and has since spread to many other sectors and pricing contexts, including media, retail, manufacturing, distribution, etc. The goal of B2B pricing science is to optimize pricing strategies by using prescriptive analytics to model and modify historical behavior. Although pricing science does not solely predict historical pricing behavior, predictive analytics is the foundation of this process. The first step in creating a pricing strategy, developing a robust and reliable prediction model, is crucially important because failing to understand historical behavior and failing to capture market dynamics leads to irrelevant price recommendations.
As facial recognition technology use generates intense scrutiny, a new system unveiled at Washington's Dulles airport is being touted as a "user friendly" way to help ease congestion for air travelers. Officials at Dulles unveiled two new face recognition systems Thursday, one to meet legal requirements for biometric entry-exit records, and a second to help speed processing of travelers arriving on international flights by matching their real-time images with stored photos. The growing use of facial recognition has ignited debate over surveillance and privacy around the world, but officials told media this system was a way to help reducing annoying lines and wait times without compromising security. "The technology works," US Customs and Border Protection Commissioner Kevin McAleenan told reporters at an airport unveiling. And we believe it will change the face of international travel."
Artificial Intelligence is perhaps the most discussed technology over the past few years. The buzz is never-ending when it comes to topics covering machine learning and data analytics and autonomous cars and other AI developments. Most of these are based on the machine learning technology that gives the system the capability to study a situation and make its own assessment on the possibilities to come to an end solution. The oft-quoted example involves banking institutions switching to AI for processing of loan applications. Now, in the conventional system, a bank loan officer would have studied the application, checked the credentials and financial history of the applicant and then would have decided to approve or reject the loan.
Detecting anomalous activity in human mobility data has a number of applications including road hazard sensing, telematic based insurance, and fraud detection in taxi services and ride sharing. In this paper we address two challenges that arise in the study of anomalous human trajectories: 1) a lack of ground truth data on what defines an anomaly and 2) the dependence of existing methods on significant pre-processing and feature engineering. While generative adversarial networks seem like a natural fit for addressing these challenges, we find that existing GAN based anomaly detection algorithms perform poorly due to their inability to handle multimodal patterns. For this purpose we introduce an infinite Gaussian mixture model coupled with (bi-directional) generative adversarial networks, IGMM-GAN, that is able to generate synthetic, yet realistic, human mobility data and simultaneously facilitates multimodal anomaly detection. Through estimation of a generative probability density on the space of human trajectories, we are able to generate realistic synthetic datasets that can be used to benchmark existing anomaly detection methods. The estimated multimodal density also allows for a natural definition of outlier that we use for detecting anomalous trajectories. We illustrate our methodology and its improvement over existing GAN anomaly detection on several human mobility datasets, along with MNIST.
Hypothesis tests are a crucial statistical tool for data mining and are the workhorse of scientific research in many fields. Here we present a differentially private analogue of the classic Wilcoxon signed-rank hypothesis test, which is used when comparing sets of paired (e.g., before-and-after) data values. We present not only a private estimate of the test statistic, but a method to accurately compute a p-value and assess statistical significance. We evaluate our test on both simulated and real data. Compared to the only existing private test for this situation, that of Task and Clifton, we find that our test requires less than half as much data to achieve the same statistical power.
For any autonomous driving vehicle, control module determines its road performance and safety, i.e. its precision and stability should stay within a carefully-designed range. Nonetheless, control algorithms require vehicle dynamics (such as longitudinal dynamics) as inputs, which, unfortunately, are obscure to calibrate in real time. As a result, to achieve reasonable performance, most, if not all, research-oriented autonomous vehicles do manual calibrations in a one-by-one fashion. Since manual calibration is not sustainable once entering into mass production stage for industrial purposes, we here introduce a machine-learning based auto-calibration system for autonomous driving vehicles. In this paper, we will show how we build a data-driven longitudinal calibration procedure using machine learning techniques. We first generated offline calibration tables from human driving data. The offline table serves as an initial guess for later uses and it only needs twenty-minutes data collection and process. We then used an online-learning algorithm to appropriately update the initial table (the offline table) based on real-time performance analysis. This longitudinal auto-calibration system has been deployed to more than one hundred Baidu Apollo self-driving vehicles (including hybrid family vehicles and electronic delivery-only vehicles) since April 2018. By August 27, 2018, it had been tested for more than two thousands hours, ten thousands kilometers (6,213 miles) and yet proven to be effective.
In case you haven't noticed, machine learning -- the practice of designing algorithms to equip computers to collect data, identify patterns, and learn from them without human interference -- has gained fresh momentum. Although the concept is not new, its recent applications gave rise to a massive digital revolution. Think self-driving cars, Netflix's recommendation engine, Uber's arrival and pick-up estimations, and Spotify's Discover Weekly playlists. Without machine learning, all these things would not exist. SEE ALSO: Robots ruin the fun of'Where's Waldo?' with facial recognition The number of businesses adopting machine learning is growing at a rapid pace, which means now is the perfect time to immerse yourself in it and become a frontrunner in the industry.