Deep learning creates virtual multiplexed immunostaining to improve cancer diagnosis

Researchers at the University of California, Los Angeles (UCLA), in collaboration with pathologists from Hadassah Hebrew ...

Loss functions and constraints improve sea surface height prediction

In order to understand currents, tides and other ocean dynamics, scientists need to accurately capture sea surface height, or ...
Tech Xplore on MSN

Decoding black box AI with human-readable data descriptions and influence

Artificial intelligence (AI), particularly deep learning models, are often considered black boxes because their ...
IEEE

An Interpretable SAR Image Filtering Algorithm

Abstract: Effective noise suppression is crucial for the subsequent interpretation tasks of synthetic aperture radar (SAR) imagery. Traditional SAR image processing techniques often overlook the ...
Morning Overview on MSN

Scientists build a ‘periodic table’ for AI models

Scientists are trying to tame the chaos of modern artificial intelligence by doing something very old fashioned: drawing a ...
EurekAlert!

AI is rewriting the rules of enzyme engineering—from faster prediction to smarter design

A research team maps the key tasks that define modern enzyme engineering—function annotation, structure modeling, and property prediction—and explain how AI methods now accelerate each step, from ...
eLife

Separating selection from mutation in antibody language models

This important study introduces a new biology-informed strategy for deep learning models aiming to predict mutational effects in antibody sequences. It provides solid evidence that separating ...
IEEE

Interpretable Individual Manatee Identification Using Sketch Images and Deep Neural Networks

Abstract: Individual manatee identification is crucial for understanding their behaviors, traits, threats, population health, etc. Traditional methods rely on photo-identification, which entail ...