蘑菇Av

Three graduate students from 蘑菇Av鈥檚 Dietrich College of Humanities and Social Sciences 鈥� ,听Joel Ye(opens in new window) 补苍诲听骋补产谤颈别濒听厂补谤肠丑(opens in new window) 鈥� are using artificial intelligence to advance neuroscience research.

Their work, co-authored with faculty and/or post-doctoral researchers from the听Department of Psychology(opens in new window),听Neuroscience Institute(opens in new window) 补苍诲听, presents new or improved methods for understanding human vision and cognition.

Luo, a Ph.D. student in the Neuroscience Institute and Machine Learning Department, has developed Brain Diffusion for Visual Exploration (BrainDiVE),听a data-driven approach to synthesize images predicted to activate different regions of the brain. This technique bypasses the current approach that requires category-specific stimuli in order to characterize differences between regions of the brain. With this new technique, researchers can improve their understanding of human visual cortex using diffusion models.听Luo worked in collaboration with Margaret M. Henderson, post-doctoral research in the Neuroscience Institute,听Leila Wehbe,听an assistant professor in the Neuroscience Institute and Machine Learning Department, and Mike Tarr, the Kav膷i膰-Moura Professor of Cognitive and Brain Science,听on the article that is available on听, a preprint server for articles published prior to peer review.

Ye, a Ph.D. student in the听Neuroscience Institute, has developed the program听Neural Data Transformer 2 (NDT2), a spatiotemporal transformer for neural spiking activity. The听model reads the pattern of spikes that occur when neurons in the brain fire in a coordinated fashion. This approach improves upon current models that are limited to individual experiments, robbing deep network models of a vast amount of potential data. NDT2 aims to leverage the various data sources that span multiple sessions, participants and experimental tasks. The ability to aggregate data opens new opportunities to听decode听behavior from brain activity efficiently.听Ye worked in collaboration with Wehbe, Jennifer Collinger and Robert Gaunt, both assistant professors in the neuroscience institute, on the article published on , a preprint server for articles published prior to peer review.

Sarch, a Ph.D. student in the Neuroscience Institute and Machine Learning Department, has developed a听technique to train neural networks to predict how the brain will respond to images from large-scale datasets of听natural scenes. Sarch has enhanced this technique by using a process called 鈥渂rain dissection鈥� to identify听how different brain regions selectivity encode听spatial features, such as depth, surface normals, curvature and object relations. Understanding听how different areas of the brain selectively encode these spatial characteristics enhances our knowledge of how听a coherent 3D percept of the world is constructed. This work will improve how researchers approach functional听characteristics of vision, specifically the human visual cortex, when viewing natural scenes. Sarch worked in听collaboration with Tarr, Wehbe, and Katerina Fragkiadaki, the JPMorgan Chase Associate Professor of Computer听Science in the Machine Learning Department, on an article to be published in the Neural Information Processing听Systems proceedings and available publicly听on听.

All three graduate students are presenting their work at the 2023听, Dec. 10鈥�16 in New Orleans.

鈥淐arnegie Mellon鈥檚 graduate students shine with their cutting-edge blend of disciplines in probing the mysteries of the mind and brain,鈥� said听Tarr, who also is head of the Department of Psychology. 鈥淎t NeurIPS, their presentations showcase an impressive command of both Computational Neuroscience and Machine Learning, reflecting deep, foundational expertise."