"Off-line" periods during AI training mitigated "catastrophic forgetting" in artificial neural networks, mimicking the learning benefits sleep provides in the human brain.
A novel deep learning method that uses graph convolutional neural networks (gCNNs) can predict cognitive function based on the brain's size and structure. The algorithm may provide insights into the relationship between brain morphology and different cognitive functions, as well as declines in cognitive function.
New machine learning models assess the connection between hundreds of clinical variables, including doctor visits and health records for seemingly unconnected conditions, to predict the likelihood of ASD in young children.
A new machine learning algorithm can predict the in-game actions of volleyball players with 80% accuracy.
Most AI models are unable to represent features of human vision, making them worse at recognizing images.
Using artificial neural networks to analyze neuroimaging data, researchers are able to accurately determine biological age.
Researchers say they have created the most bio-realistic and complex computer models of individual brain cells.
Researchers used classic fables and short stories with moral implications to test and assess human-like reasoning in artificial intelligence.
A new robotic system can learn directly from human interaction videos and generalize the information at the task being completed. This makes the robot well suited to learn household chores effectively and efficiently.
The ventral striatum plays a crucial role when it comes to choices about future pain versus future profit.
A new artificial neural network aced a wine tasting test and promises a less energy-hungry version of artificial intelligence, researchers report.
A new learning algorithm trains a robotic dog to walk within one hour, researchers report.
