Showing 20 articles starting at article 101
< Previous 20 articles Next 20 articles >
Categories: Computer Science: Artificial Intelligence (AI), Geoscience: Geomagnetic Storms
Published Engineering household robots to have a little common sense
(via sciencedaily.com) Original source Engineers aim to give robots a bit of common sense when faced with situations that push them off their trained path, so they can self-correct after missteps and carry on with their chores. The team's method connects robot motion data with the common sense knowledge of large language models, or LLMs.
Published AI can now detect COVID-19 in lung ultrasound images
(via sciencedaily.com) Original source Artificial intelligence can spot COVID-19 in lung ultrasound images much like facial recognition software can spot a face in a crowd, new research shows. The findings boost AI-driven medical diagnostics and bring health care professionals closer to being able to quickly diagnose patients with COVID-19 and other pulmonary diseases with algorithms that comb through ultrasound images to identify signs of disease.
Published Robotic metamaterial: An endless domino effect
(via sciencedaily.com) Original source If it walks like a particle, and talks like a particle... it may still not be a particle. A topological soliton is a special type of wave or dislocation which behaves like a particle: it can move around but cannot spread out and disappear like you would expect from, say, a ripple on the surface of a pond. Researchers now demonstrate the atypical behavior of topological solitons in a robotic metamaterial, something which in the future may be used to control how robots move, sense their surroundings and communicate.
Published Two artificial intelligences talk to each other
(via sciencedaily.com) Original source Performing a new task based solely on verbal or written instructions, and then describing it to others so that they can reproduce it, is a cornerstone of human communication that still resists artificial intelligence (AI). A team has succeeded in modelling an artificial neural network capable of this cognitive prowess. After learning and performing a series of basic tasks, this AI was able to provide a linguistic description of them to a 'sister' AI, which in turn performed them.
Published Advanced army robots more likely to be blamed for deaths
(via sciencedaily.com) Original source Advanced killer robots are more likely to blamed for civilian deaths than military machines, new research has revealed. The study shows that high-tech bots will be held more responsible for fatalities in identical incidents.
Published Robot ANYmal can do parkour and walk across rubble
(via sciencedaily.com) Original source The quadrupedal robot ANYmal went back to school and has learned a lot. Researchers used machine learning to teach it new skills: the robot can now climb over obstacles and successfully negotiate pitfalls.
Published How do neural networks learn? A mathematical formula explains how they detect relevant patterns
(via sciencedaily.com) Original source Neural networks have been powering breakthroughs in artificial intelligence, including the large language models that are now being used in a wide range of applications, from finance, to human resources to healthcare. But these networks remain a black box whose inner workings engineers and scientists struggle to understand. Now, a team has given neural networks the equivalent of an X-ray to uncover how they actually learn.
Published Robotic interface masters a soft touch
(via sciencedaily.com) Original source Researchers have developed a haptic device capable of reproducing the softness of various materials, from a marshmallow to a beating heart, overcoming a deceptively complex challenge that has previously eluded roboticists.
Published Going top shelf with AI to better track hockey data
(via sciencedaily.com) Original source Researchers got a valuable assist from artificial intelligence (AI) tools to help capture and analyze data from professional hockey games faster and more accurately than ever before, with big implications for the business of sports.
Published The role of machine learning and computer vision in Imageomics
(via sciencedaily.com) Original source A new field promises to usher in a new era of using machine learning and computer vision to tackle small and large-scale questions about the biology of organisms around the globe.
Published Method rapidly verifies that a robot will avoid collisions
(via sciencedaily.com) Original source A new safety-check technique can prove with 100 percent accuracy that a planned robot motion will not result in a collision. The method can generate a proof in seconds and does so in a way that can be easily verified by a human.
Published AI can speed design of health software
(via sciencedaily.com) Original source Artificial intelligence helped clinicians to accelerate the design of diabetes prevention software, a new study finds.
Published New dressing robot can 'mimic' the actions of care-workers
(via sciencedaily.com) Original source Scientists have developed a new robot that can 'mimic' the two-handed movements of care-workers as they dress an individual.
Published New AI model could streamline operations in a robotic warehouse
(via sciencedaily.com) Original source Researchers applied deep-learning approaches from vehicle routing to streamline planning trajectories for robots in an e-commerce warehouse. Their method breaks the problem down into smaller chunks and then predicts the best chunks to solve with traditional algorithms.
Published A novel method for easy and quick fabrication of biomimetic robots with life-like movement
(via sciencedaily.com) Original source Ultraviolet-laser processing is a promising technique for developing intricate microstructures, enabling complex alignment of muscle cells, required for building life-like biohybrid actuators. Compared to traditional complex methods, this innovative technique enables easy and quick fabrication of microstructures with intricate patterns for achieving different muscle cell arrangements, paving the way for biohybrid actuators capable of complex, flexible movements.
Published Method identified to double computer processing speeds
(via sciencedaily.com) Original source Scientists introduce what they call 'simultaneous and heterogeneous multithreading' or SHMT. This system doubles computer processing speeds with existing hardware by simultaneously using graphics processing units (GPUs), hardware accelerators for artificial intelligence (AI) and machine learning (ML), or digital signal processing units to process information.
Published How ancient sea creatures can inform soft robotics
(via sciencedaily.com) Original source Fossils of a marine animal that lived 500 million years ago, combined with computer simulations, informed the design of a new soft robot.
Published Why insects navigate more efficiently than robots
(via sciencedaily.com) Original source Engineers have studied how insects navigate, for the purpose of developing energy-efficient robots.
Published Innovations in depth from focus/defocus pave the way to more capable computer vision systems
(via sciencedaily.com) Original source In an image, estimating the distance between objects and the camera by using the blur in the images as clue, also known as depth from focus/defocus, is essential in computer vision. However, model-based methods fail when texture-less surfaces are present, and learning-based methods require the same camera settings during training and testing. Now, researchers have come up with an innovative strategy for depth estimation that combines the best of both the worlds to solve these limitations, extending the applicability of depth from focus/defocus.
Published A sleeker facial recognition technology tested on Michelangelo's David
(via sciencedaily.com) Original source Many people are familiar with facial recognition systems that unlock smartphones and game systems or allow access to our bank accounts online. But the current technology can require boxy projectors and lenses. Now, researchers report on a sleeker 3D surface imaging system with flatter, simplified optics. In proof-of-concept demonstrations, the new system recognized the face of Michelangelo's David just as well as an existing smartphone system.