We study an online linear optimization (OLO) problem in which the learner is provided access to K "hint" vectors in each round prior to making a decision. In this setting, we devise an algorithm that obtains logarithmic regret whenever there exists a convex combination of the K hints that has positive correlation with the cost vectors. This significantly extends prior work that considered only the case K =1. To accomplish this, we develop a way to combine many arbitrary OLO algorithms to obtain regret only a logarithmically worse factor than the minimum regret of the original algorithms in hindsight; this result is of independent interest.

This work develops a compute-efficient algorithm to tackle a fundamental problem in transportation: that of urban travel demand estimation. It focuses on the calibration of origin-destination travel demand input parameters for high-resolution traffic simulation models. It considers the use of abundant traffic road speed data. The travel demand calibration problem is formulated as a continuous, high-dimensional, simulation-based optimization (SO) problem with bound constraints. There is a lack of compute efficient algorithms to tackle this problem. We propose the use of an SO algorithm that relies on an efficient, analytical, differentiable, physics-based traffic model, known as a metamodel or surrogate model. We formulate a metamodel that enables the use of road speed data. Tests are performed on a Salt Lake City network. We study how the amount of data, as well as the congestion levels, impact both in-sample and out-of-sample performance. The proposed method outperforms the benchmark for both in-sample and out-of-sample performance by 84.4% and 72.2% in terms of speeds and counts, respectively. Most importantly, the proposed method yields the highest compute efficiency, identifying solutions with good performance within few simulation function evaluations (i.e., with small samples).

Teal's workers in Salt Lake City assemble their drones by hand, sitting at several long tables in an open workshop. There is no need for conveyor belts or automated production at their current scale. They do have one robot arm in the back, which is used to calibrate each drone's navigation systems. After calibration, they take the drones out to a grassy patch out front to run them through test flights, with the snow-capped Wasatch Mountains in the distance.

Customizable 3D avatar-based facial expression stimuli may improve user engagement in behavioral biomarker discovery and therapeutic intervention for autism, Alzheimer's disease, facial palsy, and more. However, there is a lack of customizable avatar-based stimuli with Facial Action Coding System (FACS) action unit (AU) labels. Therefore, this study focuses on (1) FACS-labeled, customizable avatar-based expression stimuli for maintaining subjects' engagement, (2) learning-based measurements that quantify subjects' facial responses to such stimuli, and (3) validation of constructs represented by stimulus-measurement pairs. We propose Customizable Avatars with Dynamic Facial Action Coded Expressions (CADyFACE) labeled with AUs by a certified FACS expert. To measure subjects' AUs in response to CADyFACE, we propose a novel Beta-guided Correlation and Multi-task Expression learning neural network (BeCoME-Net) for multi-label AU detection. The beta-guided correlation loss encourages feature correlation with AUs while discouraging correlation with subject identities for improved generalization. We train BeCoME-Net for unilateral and bilateral AU detection and compare with state-of-the-art approaches. To assess construct validity of CADyFACE and BeCoME-Net, twenty healthy adult volunteers complete expression recognition and mimicry tasks in an online feasibility study while webcam-based eye-tracking and video are collected. We test validity of multiple constructs, including face preference during recognition and AUs during mimicry.

Kara Frederick, tech director at the Heritage Foundation, discusses the need for regulations on artificial intelligence as lawmakers and tech titans discuss the potential risks. Meta has acknowledged that it used public posts on its Facebook and Instagram platforms to train its new artificial intelligence virtual assistant. Meta President of Global Affairs Nick Clegg said that the company used only public posts and stayed clear of both private posts that were shared with friends and family as well as private messages to train the company's AI bot, according to a report from Reuters. "We've tried to exclude datasets that have a heavy preponderance of personal information," Clegg said during the company's annual Connect conference, adding that the "vast majority" of the data used was already publicly available. Mark Zuckerberg, CEO and founder of Facebook Inc., speaks during the Silicon Slopes Tech Summit in Salt Lake City on Jan. Tech companies have been under fire in recent months over reports that they have been using information from the internet with permission to train AI models, which are capable of sorting through a massive amount of data. "AI's need staggering amounts of training data, so user posts are an ideal way to'feed the beast,'" Christopher Alexander, chief analytics officer of Pioneer Development Group, told Fox News Digital.

A NASA space capsule carrying the largest soil sample ever collected from the surface of an asteroid has landed in the Utah desert seven years after the mission's launch. Flight Control announced on Sunday. The gumdrop-shaped capsule, released from the robotic spacecraft OSIRIS-REx as the mothership passed within 108,000km (67,000 miles) of Earth hours earlier, touched down within a designated landing zone west of Salt Lake City on the United States military's vast Utah Test and Training Range. The samples will be flown on Monday to a new lab at NASA's Johnson Space Center in Houston. The building already houses nearly 400kg (842lb) of moon rocks gathered by the Apollo astronauts more than a half-century ago.

It sounds like the stuff of science fiction - but a company in Utah has already implanted brain chips in dozens of patients. Blackrock Neurotech, based in Salt Lake City, has the grand ambition of curing physical paralysis, blindness, deafness and depression. The chip -- known as NeuroPort Array -- allow people to control robotic arms and wheelchairs, play video games and even feel sensations. It works by using nearly 100 microneedles that attach to the brain and read electrical signals produced by someone's thoughts. More than three dozen people have so far received it.

Full-field traffic state information (i.e., flow, speed, and density) is critical for the successful operation of Intelligent Transportation Systems (ITS) on freeways. However, incomplete traffic information tends to be directly collected from traffic detectors that are insufficiently installed in most areas, which is a major obstacle to the popularization of ITS. To tackle this issue, this paper introduces an innovative traffic state estimation (TSE) framework that hybrid regression machine learning techniques (e.g., artificial neural network (ANN), random forest (RF), and support vector machine (SVM)) with a traffic physics model (e.g., second-order macroscopic traffic flow model) using limited information from traffic sensors as inputs to construct accurate and full-field estimated traffic state for freeway systems. To examine the effectiveness of the proposed TSE framework, this paper conducted empirical studies on a real-world data set collected from a stretch of I-15 freeway in Salt Lake City, Utah. Experimental results show that the proposed method has been proved to estimate full-field traffic information accurately. Hence, the proposed method could provide accurate and full-field traffic information, thus providing the basis for the popularization of ITS.

Editor's note: This is part of a KSL.com series looking at the rise of artificial intelligence technology tools such as ChatGPT, the opportunities and risks they pose and what impacts they could have on various aspects of our daily lives. SALT LAKE CITY -- Like all lawmakers in Utah's citizen Legislature, House Majority Whip Jefferson Moss spends most of the year working a day job. Moss, a Republican from Saratoga Springs, has a background in venture capital and technology, so he was quick to see the potential for artificially intelligent chatbots like ChatGPT when it was released last November. And while government as a whole can be slow to adopt new technology, Moss already sees recent breakthroughs in AI technology as huge leaps forward. "I've been following different iterations of AI, but when ChatGPT came out, it really was a game-changer," Moss told KSL.com in March.

This article contains spoilers for The Last of Us Episode 9, "Look for the Light." The Last of Us has been roundly praised as the best video-game adaptation ever made, even the first to be truly great, and part of that greatness is that you don't need to have played the original games to appreciate it. Although the HBO series is replete with moments from the games repeated beat for beat and even shot for shot, it's not hobbled by mindless fidelity to its source, and it finds ways to exploit its new medium that would never work if you were sitting in front of the TV with a PlayStation controller instead of a remote control. But in the final episode of the first season, "Look for the Light," The Last of Us returns to its source material in a way that comes close to wrecking everything the show has accomplished. Joel and Ellie have finally reached the goal they've been headed toward the entire season: the Firefly encampment in Salt Lake City. Joel has spent the past 20 years grieving the murder of his teenage daughter, Sarah, at the beginning of the Cordyceps pandemic, and the more recent death of his partner, Tess, and an uneasy reunion with his brother has underlined the lesson that it's best for him not to care for anyone at all.