Articles on Computer vision
Displaying all articles
All the training data in the world can’t account for every possibility when AI systems interact with people and the environment.
People and computers perceive the world differently, which can lead AI to make mistakes no human would. Researchers are working on how to bring human and AI vision into alignment.
Research asking AI models to describe and generate pictures reveals they see a bright, sensational world of generic images.
It might seem like an obvious move to deploy drones to help look for flood victims, but floods pose unique challenges that stymie the technology.
AI often has trouble interpreting optical illusions. A new kind of neural network starts to bridge the gap
Understanding when and how neurons die is an important part of research on neurodegenerative diseases like Lou Gehrig’s, Alzheimer’s and Parkinson’s diseases.
Using a form of artificial intelligence called deep neural networks, researchers can generate new proteins from scratch without having to consult nature.
Computerized systems that automatically determine whether a pitch is a ball or strike promise to make umpiring more accurate, but at what price?
Brain functions integrate and compress multiple components of an experience, including sight and smell – which simply can’t be handled in the way computers sense, process and store data.
Drones already help with search and rescue, but teaching machines to identify victims on their own could free up human rescuers to do other crucial work.









