Machine learning & AI

Credit: Xie et al. To efficiently navigate their surrounding environments and complete missions, unmanned aerial systems (UASs) should be able to detect multiple objects in their surroundings and track their movements over time. So far, however, enabling multi-object tracking in unmanned aerial vehicles has proved to be fairly challenging. Researchers...

Egocentric 4D Live Perception (Ego4D) is a massive-scale dataset that compiles 3,025 hours of footage from the wearable cameras of 855 participants in nine countries. Credit: Ego4D The University of Bristol is part of an international consortium of 13 universities in partnership with Facebook AI, that collaborated to advance egocentric...

MIT researchers have demonstrated that a special class of deep learning neural networks is able to learn the true cause-and-effect structure of a navigation task during training. Credit: Massachusetts Institute of Technology Neural networks can learn to solve all sorts of problems, from identifying cats in photographs to steering a...

A dataset that was used to create crash-risk maps covered 7,500 square kilometers from Los Angeles, New York City, Chicago and Boston. Among the four cities, L.A. was the most unsafe, since it had the highest crash density, followed by New York City, Chicago and Boston. Credit: MIT CSAIL Today's...

Diagram summarizing the pipeline of the model devised by the researchers. Credit: Basu et al. Over the past decade or so, computer scientists developed a variety of machine learning (ML) models that can analyze large amounts of data both quickly and efficiently. To be applied in real-world situations that involve...

Left: X-ray of lost "Lonesome Crouching Nude" found beneath Picasso's "The Blind Man's Meal." Credit: Estate of Pablo Picasso. Right: Full color recreation. Credit: Oxia Palus. A painting of a naked woman by Pablo Picasso that has been hidden beneath one of his "Blue Period' masterpieces for more than a century...

ABNN's gradual focus on specific line-spectrum features of a ship. Credit: Institute of Acoustics, Chinese Academy of Sciences In underwater acoustics, deep learning is gaining traction in improving sonar systems to detect ships and submarines in distress or in restricted waters. However, noise interference from the complex marine environment becomes...

A researcher flies a drone over an apple orchard at Penn State's Russell E. Larson Agricultural Research Center. The drone was used to shoot a video of the demonstration of the over-current driven LED lights machine vision mechanism. Credit: Penn State A novel camera system using active lighting devised by Penn...

(a) Universal adversarial examples: Adding a small amount of carefully crafted noise to a certain image could make it become an adversarial example that can fool different quantum classifiers. (b) Universal adversarial perturbations: adding the same carefully-crafted noise to a set of images could make them all become adversarial examples...

AI-generated images of "a stained glass window with an image of a blue strawberry." Credit: OpenAI A major new report on the state of artificial intelligence (AI) has just been released. Think of it as the AI equivalent of an Intergovernmental Panel on Climate Change report, in that it identifies...

Diagram of interplay between data, transfer operators, kernel methods, and environmental features. Transfer operators represent dynamical systems, where a state x ∈ X is lifted to a space L∞X and g(x) provides physical properties of the system. Many systems are defined by data exhibiting complex patterns, such as two nested...

Fig. 1: System Model and FAMHE workflow. All entities are interconnected (dashed lines) and communication links at each step are shown by thick arrows. All entities (data providers (DPs) and querier) are honest but curious and do not trust each other. In 1. the querier sends the query (in clear)...

Graphical abstract. Credit: DOI: 10.1016/j.patter.2021.100348 Creating human-like AI is about more than mimicking human behavior—technology must also be able to process information, or "think" like humans if it is to be fully relied upon. New research, published in the journal Patterns and led by the University of Glasgow's School of...

In this Jan. 16, 2021 file photo, Eric Lander speaks during an event at The Queen theater in Wilmington, Del. Top science advisers to President Joe Biden are calling for a new "bill of rights" to guard against powerful new artificial intelligence technology, Friday, Oct. 8. Lander, Biden's chief science...

An illustration combining different agents in a single round of play at the card game Lord of the Rings. Credit: Godlewski & Sawicki. When machine learning algorithms and other computational tools started becoming increasingly advanced, many computer scientists set out to test their capabilities by training them to compete against...

Equipping computer models with “covert cognizance” could protect electric grids, manufacturing facilities and nuclear power plants from hackers, says Hany Abdel-Khalik, a Purdue associate professor of nuclear engineering. Credit: Purdue University / Vincent Walter It sounds like a scene from a spy thriller. An attacker gets through the IT defenses...

Assistant Professor Eeva Vilkkumaa. Credit: Aalto University / Kukka-Maria Rosenlund Decision analysis is a field that develops analytical models for better decision-making. One interesting question is whether artificial intelligence can replace people as decision makers—and if, then under what circumstances. AI algorithms that make decisions are prevalent. They choose appropriate...

Secure AI Labs is expanding access to encrypted health care data to advance AI-driven innovation in the field. Credit: Jose-Luis Olivares, MIT There's a lot of excitement at the intersection of artificial intelligence and health care. AI has already been used to improve disease treatment and detection, discover promising new...

The autonomous drone navigates independently through the forest at 40 km/h. Credit: UZH Researchers at the University of Zurich have developed a new approach to autonomously fly quadrotors through unknown, complex environments at high speeds using only on-board sensing and computation. The new approach could be useful in emergencies, on...

Credit: California Institute of Technology Researchers at Caltech have built a bipedal robot that combines walking with flying to create a new type of locomotion, making it exceptionally nimble and capable of complex movements. Part walking robot, part flying drone, the newly developed LEONARDO (short for LEgs ONboARD drOne, or...