Compared to standard machine learning models, deep learning models are largely superior at discerning patterns and discriminative features in brain imaging, despite being more complex in their architecture. Advanced biomedical technologies such as structural and functional magnetic resonance imaging (MRI and fMRI) or genomic sequencing have produced an enormous volume of data about the human…

Just like explorers need maps, scientists require guides to better understand and advance new technology. A neuromorphic device, which can mimic the neural cells in our brain, has lacked such a guideline and created headaches for scientists trying to understand their operational mechanisms. That is until now after a research group created a map that…

People with autism spectrum disorder interpret facial expressions differently. Researchers have revealed more about how this comes to be. They induced abnormalities into a neural network model to explore the effects on the brain’s learning development. Using a neural network model that reproduces the brain on a computer, a group of researchers based at Tohoku…

A new analysis shows that researchers using machine learning methods could risk underestimating uncertainties in their final results. The Standard Model of particle physics offers a robust theoretical picture of the fundamental particles, and most fundamental forces which compose the universe. All the same, there are several aspects of the universe: from the existence of…

Data from one of the first clinical uses of augmented reality guidance with electromagnetically tracked tools shows that the technology may help doctors quickly, safely, and accurately deliver targeted liver cancer treatments, according to new research. «Converting traditional two-dimensional imaging into three-dimensional holograms which we can then utilize for guidance using augmented reality helps us…

Scientists are evaluating machine-learning models using transfer learning principles. In data-driven machine learning, models are built to make predictions and estimations for what’s to come in any given data set. One important field within machine learning is classification, which allows a data set to be assessed by an algorithm and then classified or broken down…

Researchers have found that a machine learning algorithm can predict the location of actin-associated proteins in lamellipodia and other subcellular structures based solely on the location of actin itself. This approach could be useful for rapid analysis of microscopy images, and potentially as a substitute for using fluorescent stains to detect proteins within cells. In…

A new artificial-intelligence technology for heart imaging can improve care for patients, allowing doctors to examine their hearts for scar tissue while eliminating the need for contrast injections. A team of researchers who developed the technology, including doctors at UVA Health, reports the success of the approach in a new article in the scientific journal…

Researchers employed generative adversarial networks to more accurately construct datasets for aerial images of building that are obscured by clouds. This work may lead to improved image recognition algorithms. Machine learning is a powerful method for accomplishing artificial intelligence tasks, such as filling in missing information. One popular application is repairing images that are obscured,…

Researchers have developed an ionic artificial vision device capable of increasing the edge contrast between the darker and lighter areas of an mage in a manner similar to that of human vision. This first-ever synthetic mimicry of human optical illusions was achieved using ionic migration and interaction within solids. It may be possible to use…