Bridging the gap of neuronal communication by means of intelligent hybrid systems

Keith Bush

Gabriella Panuccio

Assistant Professor


External collaborator

I hold a degree in Chemical Engineering and a Ph.D. in Computer Science.

My research interests focus on machine learning and control theoretic approaches to real-time human neuroimaging, using both real-time fMRI and fMRI-based neurofeedback to understand and exploit volitional regulation of emotion.

By understanding how the human brain decodes and integrates neurofeedback signals into its processing, I hope to optimize neuroimaging studies and develop new control theoretic treatments for emotional disorders.

I received the degree in Chemical Engineering from the University of Pennsylvania and the doctoral degree in Computer Science from Colorado State University. My doctoral research explored mathematical structures for implementing adaptive control systems, e.g., reinforcement learning, to real-world nonlinear dynamical systems.

In 2008 I accepted a postdoctoral fellowship with Dr. Joelle Pineau of McGill University where I applied real-time adaptive control systems to suppress epileptiform activity in animal models of epilepsy. This work was done in collaboration with the neurophysiology team of which Gabriella Panuccio was a researcher at the Montreal Neurological Institute.

In 2010 I joined the faculty at the University of Arkansas at Little Rock and established a machine learning collaboration with the University of Arkansas for Medical Sciences (UAMS) to analyze multimodal neuroimaging and behavioral datasets.

Since 2015 I have joined the Dept. of Psychiatry at UAMS as assistant professor in the Brain Imaging Research Center (BIRC).

James GA, Hazaroglu O, Bush KA. (2016). A human brain atlas derived via n-cut parcellation of resting-state and task-based fMRI data. Magn Reson Imaging. 34(2):209-18. doi

Stinson PW and Bush KA. (2013). Exogenous control and dynamical reduction of echo state networks. Neural Networks (IJCNN), The 2013 International Joint Conference on, Dallas, TX, pp. 1-7. doi

Bush K, Panuccio G, Avoli M, Pineau J. (2012). Evidence-based modeling of network discharge dynamics during periodic pacing to control epileptiform activity. J Neurosci Methods. 204:318-25. doi

Anderson CW, Young PM, Buehner MR, Knight JN, Bush KA, Hittle DC. (2007). Robust reinforcement learning control using integral quadratic constraints for recurrent neural networks. IEEE Trans Neural Netw. 18(4):993-1002. doi

UAMS - Brain Imaging Research Center (BIRC)

Dept. of Psychiatry

4224 Shuffield Dr.

Mail Slot # 554

Little Rock, AR, 72205

United States