Data scientist, engineer and neuroscientist with over 12 years of experience in the collection, analysis, and interpretation of biological data. Expertise in using a variety of machine learning techniques, including artificial neural networks, dimensionality reduction, optimization, and linear dynamical systems to answer scientific questions. Demonstrated ability to communicate scientific findings to a diverse audience with 18 peer-reviewed publications (5 first-author) and over 13 presentations at scientific conferences.
Education and Training
Postdoctoral Researcher, Dept. of Elec. and Comp. Engr., Carnegie Mellon University (July 2019 — September 2020)
Postdoctoral Researcher, Systems Neuroscience Institute, Univ. Pittsburgh (Nov 2014 — June 2019)
Ph.D. Bioengineering, Neural Engineering, University of Pittsburgh (Aug 2007 — Oct 2014)
- Dissertation: Evaluation and advancement of electrocorticographic brain-machine interfaces for individuals with upper-limb paralysis.
B.S. Chemical and Biomolecular Engineering, The Ohio State University (Sept 2000 — Aug 2005)
Allen Institute for Brain Science
Scientist II, Neural Coding
- Investigation of visual coding properties of large-scale optical physiology datasets.
- Development of an image co-registration pipeline for linking single-cell gene expression profiles to calcium imaging recordings.
Carnegie Mellon University
Postdoctoral Research Associate, Yu Laboratory, Department of Electrical and Computer Engineering
- Developed analytical techniques for characterizing high-dimensional neural population dynamics.
- Used dimensionality reduction and optimization techniques to analyze the dynamics of multi-electrode neural recordings during BCI control.
- Designed and implemented a real-time BCI decoding framework based on Gaussian process factor analysis.
University of Pittsburgh
Postdoctoral Fellow, Batista Laboratory, Systems Neuroscience Institute
- Developed a stabilized BCI framework based on manifold subspace alignment to improve the reliability of neural interfaces.
- Utilized dimensionality reduction, decoding, and optimization techniques to visualize and analyze high-dimensional neural population recordings.
- Supervised the research activities of 4 graduate students, 2 undergraduate students, and 2 technicians.
University of Pittsburgh
Graduate Research Assistant, Human Rehabilitation and Neural Engineering Laboratory
- Designed and conducted research assessing the ability of tetraplegic and epileptic clinical populations to control an electrocorticographic (ECoG) BCI.
- Developed a novel neural decoding algorithm based on Empirical Bayes to improve extraction of BCI control signals from electrical field potential recordings.
- Led the development of a closed-loop software system for real-time acquisition, analysis, and decoding of ECoG signals to control prosthetic limbs and computer interfaces.
- Developed MRI and CT-based localization protocols to identify cortical electrode array implantation sites.
Analytical Techniques: Neural networks, reinforcement learning, dimensionality reduction (PCA, factor analysis), decoding (regression, kalman filtering, clustering, classification), Gaussian processes, optimization, time-frequency signal analysis, time series analysis, data visualization, medical image analysis.
Programming Languages/Platforms/Etc: Python, MATLAB, Tensorflow/Keras, C/C++, SQL, LabVIEW, PHP, CSS, HTML, Git, SVN.
Relevant Coursework: Machine Learning (taken at Carnegie Mellon Univ.), Neural Signal Processing (Carnegie Mellon Univ.), Computational Neuroscience Methods, Time-frequency Signal Analysis, Statistical Methods for Neuroscience and Psychology, Methods in Medical Image Analysis (Carnegie Mellon Univ.).
AD Degenhart, WE Bishop, ER Oby, EC Tyler-Kabara, SM Chase, AP Batista, BM Yu. (2018). A stabilized brain-computer interface based on neural manifold alignment. Provisional U.S. Patent Application No. 62/763,874.