Researchers set sights on theory of deep learning
Rice's Richard Baraniuk and Moshe Vardi are part of a multiuniversity team of engineers, computer scientists, mathematicians and statisticians tapped by the Office of Naval Research to develop a principled theory of deep learning.
Small quake clusters can’t hide from AI
A deep learning algorithm developed at Rice University analyzes data from a deadly landslide in Greenland to show how it may someday predict seismic events like earthquakes and volcanic eruptions.
Early Bird uses 10 times less energy to train deep neural networks
Rice engineers have found a way to train deep neural networks for a fraction of the energy required today. Their Early Bird method finds key network connectivity patterns early in training.
Deep learning rethink overcomes major obstacle in AI industry
Rice University computer scientists have overcome a major obstacle in the burgeoning artificial intelligence industry.
Cameras see around corners in real time with deep learning
Rice researchers and collaborators have created an imaging system that can see detailed objects around corners in real time.
