Showing 20 articles starting at article 361

< Previous 20 articles        Next 20 articles >

Categories: Computer Science: Artificial Intelligence (AI), Mathematics: Statistics

Return to the site home page

     (via sciencedaily.com) 

A new study shows machine-learning models trained using simple symptoms, demographic features are effective in predicting COVID-19 infections.

     (via sciencedaily.com) 

Self-driving cars need to implement efficient, effective, and accurate detection systems to provide a safe and reliable experience to its users. To this end, an international research team has now developed an end-to-end neural network that, in conjunction with the Internet-of-Things technology, detects object with high accuracy (> 96%) in both 2D and 3D. The new method outperforms the current state-of-the-art methods and the way to new 2D and 3D detection systems for autonomous vehicles.

     (via sciencedaily.com) 

In a survey and study of hospital employee volunteers, researchers found that a low-cost computer vision system was feasible and well received.

     (via sciencedaily.com) 

Engineers have created a soft robot capable of detecting when and where it was damaged -- and then healing itself on the spot.

     (via sciencedaily.com)     Original source 

Machine learning drives self-discovery of pulses that stabilize quantum systems in the face of environmental noise.

     (via sciencedaily.com) 

Imagine a team of humans and robots working together to process online orders -- real-life workers strategically positioned among their automated coworkers who are moving intelligently back and forth in a warehouse space, picking items for shipping to the customer. This could become a reality sooner than later, thanks to researchers who are working to speed up the online delivery process by developing a software model designed to make 'transport' robots smarter.

     (via sciencedaily.com) 

Research finds using a large collection of simple, un-curated synthetic image generation programs to pretrain a computer vision model for image classification yields greater accuracy than employing other pretraining methods that are more costly and time consuming, and less scalable.

     (via sciencedaily.com) 

A new technique enables artificial intelligence agents to think much farther into the future when considering how their behaviors can influence the behaviors of other AI agents, toward the completion of a task. This approach improves long-term performance of cooperative or competitive AI agents.

     (via sciencedaily.com) 

Quantum computers promise significantly shorter computing times for complex problems. But there are still only a few quantum computers worldwide with a limited number of so-called qubits. However, quantum computer algorithms can already run on conventional servers that simulate a quantum computer. A team has succeeded in calculating the electron orbitals and their dynamic development using an example of a small molecule after a laser pulse excitation. In principle, the method is also suitable for investigating larger molecules that cannot be calculated using conventional methods.

     (via sciencedaily.com) 

Researchers have developed a new model to describe how biological or technical systems form complex structures without external guidance.

     (via sciencedaily.com)     Original source 

Researchers discuss how mimicking sleep patterns of the human brain in artificial neural networks may help mitigate the threat of catastrophic forgetting in the latter, boosting their utility across a spectrum of research interests.

     (via sciencedaily.com)     Original source 

Inspired by the biomechanics of the manta ray, researchers have developed an energy-efficient soft robot that can swim more than four times faster than previous swimming soft robots. The robots are called 'butterfly bots,' because their swimming motion resembles the way a person's arms move when they are swimming the butterfly stroke.

     (via sciencedaily.com) 

A new statistical method provides a more efficient way to uncover biologically meaningful changes in genomic data that span multiple conditions -- such as cell types or tissues.

     (via sciencedaily.com)     Original source 

America was unprepared for the magnitude of the pandemic, which overwhelmed many counties and filled some hospitals to capacity. A new study suggests there may have been a mathematical method, of sorts, to the madness of those early COVID days.

     (via sciencedaily.com) 

People often wonder why one nutritional study tells them that eating too many eggs, for instance, will lead to heart disease and another tells them the opposite. The answer to this and other conflicting food studies may lie in the use of statistics, according to a new report.

     (via sciencedaily.com) 

Researchers followed the birth and death of tens of thousands of nematode worms using the 'Lifespan Machine', which collects lifespan data at unprecedented statistical resolution. They found that worms have at least two distinct 'biological ages', and that these have consistent correlations between each other, suggesting the existence of an invisible hierarchical structure that regulates the ageing process. The findings challenge the idea of living organisms having a single, universal biological age. It also means mean that biomarkers used to assess biological age can be changed by interventions such as diet, exercise, or drug treatments without actually turning a 'fast ager' into a 'slow ager'. The study calls into question the use of ageing biomarkers -- what exactly are they measuring?

     (via sciencedaily.com) 

The contact.engineering platform enables users to create a digital twin of a surface and thus to help predict, for example, how quickly it wears out, how well it conducts heat, or how well it adheres to other materials.

     (via sciencedaily.com) 

A commentary advocates the proper application of artificial intelligence in healthcare and warns of the dangers when machine learning algorithms are misused.

     (via sciencedaily.com) 

Scientists have developed a method to identify symmetries in multi-dimensional data using Bayesian statistical techniques. Bayesian statistics has been in the spotlight in recent years due to improvements in computer performance and its potential applications in artificial intelligence. However, this statistical approach requires complex calculations of integrals, which are often considered approximations only. In their new study, the research team successfully derived new exact integral formulas. Their findings contribute to improving the accuracy of methods to identify data symmetries, possibly extending their applications to wider areas of interest, such as genetic analysis.

     (via sciencedaily.com) 

A groundbreaking Bayesian method and new statistical analyses of genomic data from geckos in the Philippines shows that during the ice ages, the timing of gecko diversification gives strong statistical support for the first time to the Pleistocene aggregate island complex (PAIC) model of diversification, or 'species pump.'