Articles tagged with Autoencoders
Researchers developed a computer method to quantify myelin patterns in the brain, revealing signs of injury in damaged tissues. The approach uses convolutional autoencoders to compress information into numbers, producing unsupervised maps that separate tissue regions with distinct properties.
Avishek Choudhury, a WVU researcher, has won the NSF CAREER award to study how healthcare providers' trust in artificial intelligence changes over time. His goal is to humanize algorithms behind AI and improve decision-making quality and patient safety.
Researchers developed a new training technique, HarmonyGNN, to improve the accuracy of graph neural networks in heterophilic graphs. The framework achieved state-of-the-art performance on four heterophilic graphs with accuracy improvements ranging from 1.27% to 9.6%.
The Stowers Institute has appointed its first AI Fellow, Sumner Magruder, to harness the potential of artificial intelligence in biological research. He will collaborate with researchers to design new algorithms and unlock insights from large datasets.
Researchers at Institute of Science Tokyo developed a new framework for generative diffusion models by reinterpreting Schrödinger bridge models as variational autoencoders. This approach reduces computational costs and prevents overfitting, enabling more efficient generative AI models with broad applicability.
Researchers at Linköping University developed an AI-based method applicable to various medical and biological issues, accurately estimating people's chronological age and determining smoking status. The models identify previously known epigenetic markers used in other models, but also new markers associated with conditions.
Researchers have developed a new software based on artificial intelligence that can help interpret complex data. The software, called disentangled variational autoencoder network (β-VAE), uses two neural networks to compress and reconstruct data, allowing humans to understand the underlying core principle without prior knowledge.
A new deep-learning algorithm called TadGAN has been developed to detect anomalies in time series data, outperforming traditional methods. The algorithm combines the strengths of generative adversarial networks and autoencoders to strike a balance between vigilance and false positives.
Researchers at MIT developed a model that learns a compact state representation for soft robots, optimizing movement control and material design parameters. This enables 2D and 3D soft robots to complete tasks quickly and accurately in simulations.