Latest News

 

JavaScript findLinksAndSetTargets()
(to open ext. links in new window)

Story Highlights

Researchers from The University of Texas at Austin used artificial neural networks to predict with greater accuracy than ever before how different areas in the brain respond to specific words.

The work employed a type of recurrent neural network called long short-term memory that includes in its calculations the relationships of each word to what came before to better preserve context.

The team relied on powerful supercomputers at the Texas Advanced Computing Center to train the recurrent neural network and to run a series of computationally-intensive experiments.

The experiments also explored which parts of the brain were more sensitive to the amount of context included and the results matched the common understanding of hierarchies in the brain.


Contact

Faith Singer

Communications Manager
faith@tacc.utexas.edu | 512-232-5771

Aaron Dubrow

Science And Technology Writer
aarondubrow@tacc.utexas.edu

Jorge Salazar

Technical Writer/Editor
jorge@tacc.utexas.edu | 512-475-9411