Learning to Read Minds

Dr. Shuiwang Ji, a professor in the Department of Computer Science and Engineering, is collaborating with computer scientists and neuroscientists from a dozen institutions to test the best methods for digitally re-creating our brain structure. He and his team are part of an international initiative called BigNeuron, which seeks to comprehensively map the brain by capturing the unique shape and characteristics of individual neurons.

The human brain contains hundreds of billions of neurons working together in intricate 3D treelike structures. Reconstructing these structures would shed more light on how the brain functions and changes over time, giving valuable insight into its mysterious mechanisms. Ji and BigNeuron want to accomplish that through deep learning algorithms, a form of artificial intelligence.

Eventually, they plan to release their data sets and algorithms publicly so that neuroscientists and other researchers around the world can use their tools to fight devastating illnesses, address life-changing disorders and explore the brain’s untapped potential. Scientists have been developing brain reconstruction methods for four decades, and the ongoing research from Ji and his international collaborators represents a remarkable stride toward a mind-blowing breakthrough.