Neural nets used to rethink material design
The microscopic structures and properties of materials are intimately linked, and customizing them is a challenge. Rice University engineers are determined to simplify the process through machine learning.
Pedram Hassanzadeh wins NSF CAREER Award
Atmospheric blocking is known to cause or exacerbate extreme weather events, but much about them remains a mystery. Rice University fluid dynamicist Pedram Hassanzadeh has won a prestigious National Science Foundation CAREER Award to study these events with an eye toward better understanding the physics behind their complex mechanics.
Rice, Intel optimize AI training for commodity hardware
New AI software trains deep neural networks 15 times faster than platforms based on graphics processors.
Bioinformatics tool accurately tracks synthetic DNA
A Rice computer science lab challenges -- and beats -- deep learning in a test to see if a new bioinformatics approach effectively tracks the lab of origin of a synthetic genetic sequence.
AI-powered microscope could check cancer margins in minutes
Researchers from Rice University and MD Anderson Cancer Center have created a microscope that uses artificial intelligence to quickly and inexpensively image large tissue sections at high resolution with minimal preparation. If clinically validated, the DeepDOF microscope could allow surgeons to inspect tumor margins within minutes.
Bad news for fake news: Rice research helps combat social media misinformation
Improved use of machine learning can double throughput of real-time information filters, Rice researchers find.
Deep learning gives drug design a boost
A computational tool created at Rice University may help pharmaceutical companies expand their ability to investigate the safety of drugs.
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.
