Patrick Marino, Ph.D.
University of Pittsburgh
Data scientist and bioengineer who applies machine learning and signal processing techniques to gain insights from complex neural data. I use brain-computer interfaces to study the neural control of movement with Aaron Batista, Byron Yu, and Steve Chase.
Projects and publications
A "posture subspace" in primary motor cortex
In preparation (2023)
The nervous system combines information about body posture and movement goal to program every movement we make. Motor cortex (M1) plays an important role in this process, but little is understood about how posture and goal information are organized in M1 activity to promote the generation of motor commands. We trained monkeys to complete a variety of motor tasks while we systematically changed their arm posture. We found that posture and goal signals were organized into separate subspaces of motor cortex population activity, suggesting a mechanism by which motor cortex may flexibly combine this information to generate motor commands.
A neural basis of choking under pressure
In preparation (2023); PNAS (2019)
Motor performance typically improves as incentives increase. But, when incentives get too high, we can "choke under pressure," underperforming when it matters most. What neural processes might lead us to choke under pressure? To answer this question, we developed a challenging reaching paradigm in which monkeys exhibited decreased performance when the stakes were high. We found that these high-stakes scenarios lead to a collapse in neural information about upcoming movements, and we show that this corresponds to suboptimal reach planning. This provides a potential neural basis for choking under pressure.
Temporal constraints on sequences of motor cortical activity
In preparation (2022)
Network models posit that neural trajectories evolve according to flow fields that arise from underlying network connectivity. However, it is unclear whether experimentally-observed neural activity is actually constrained by flow fields. We used a brain-computer interface to demonstrate that temporal sequences of neural activity cannot be flexibly modified, suggesting constraints on neural activity imposed by an underlying flow field.
Towards a robust movement onset decoder for ECoG-based
brain-computer interfaces
Master's Thesis, University of Texas at Austin (2018)
Electrocorticography (ECoG) has shown promise as a recording modality for brain-computer interface applications. However, further work is needed to make ECoG-driven BCIs safe and reliable. One way to improve their safety is to prevent unwanted robotic motion until detecting the user's intent to begin a new movement. We used features of neural activity known to accompany movement onset to create a decoder which detected whether or not the user was trying to begin a movement. Our decoder had a low false-positive rate while maintaining sufficient sensitivity for online control, suggesting a path forward for eliminating unwanted robotic motion in ECoG BCIs.
Skills and Experience
Data science and machine learning
I use machine learning and statistics to make sense of complex neural and physiological data, ultimately gaining insights about how the brain controls our movements. I'm proficient in standard methods for regression, classification, and dimensionality reduction.
Science communication
I tell stories with data, communicating complicated ideas in simple ways to help others understand them.
Signal processing
Before analyzing data, I preprocess raw signals using standard filtering, smoothing, and artifact removal techniques.
Experimental design and data collection
I design and conduct experiments which carefully remove confounds to reveal relationships between variables of interest.
Mechanical design and fabrication
I design and fabricate mechanical and mechatronic devices for use in experiments, utilizing CAD, statics, dynamics, and robotics in the process.
CV
Education
University of Pittsburgh, Ph.D. in Bioengineering (expected 2023)
University of Texas at Austin, M.S.E. in Mechanical Engineering (2018)
University of Notre Dame, B.S. in Physics and B.S. in Mechanical Engineering (2015)
Experience
Doctoral student | University of Pittsburgh (2018-present)
Advised by Aaron Batista and Byron Yu
The influence of posture and reward signals on motor cortical population activity
Master's student | University of Texas at Austin (2015-2018)
Advised by Ashish Deshpande
Towards a robust reach onset decoder for electrocorticography-based BCI’s
REU Summer Research Assistant | Georgia Institute of Technology (2014)
Advised by Patricio Vela
A low‐cost, wheelchair‐mounted robotic arm to assist paralyzed patients
Publications
(* = equal contribution; ** = equal senior author contribution)
Smoulder, A.L.*, Pavlovsky, N.P.*, Marino, P.J.*, Degenhart, A.D., McClain, N.T., Batista, A.P.**, Chase, S.M.** (2021) Monkeys exhibit a paradoxical decrease in performance in high-stakes scenarios. Proceedings of the National Academy of Sciences, 118 (35) e2109643118.
Publications in Preparation
Marino, P.J., Bahureksa, L.A., Fisac, C., Oby, E.R., Motiwala, A., Grigsby, E.M., Smoulder, A.L., Degenhart, A.D., Joiner, W.M., Chase, S.M., Yu, B.M., Batista, A.P. (2023) A "posture subspace" in primary motor cortex.
Smoulder, A.L., Marino, P.J., Pavlovsky, N.P., Oby, E.R., Snyder, S.E., Bishop, W.E., Yu, B.M., Chase, S.M.**, Batista, A.P.** (2023) A neural basis for choking under pressure.
Degenhart, A.D.*, Grigsby, E.M.*, Oby, E.R.*, Motiwala, A., McClain, N.T., Marino, P.J., Batista, A.P.**, Yu, B.M.**. (2023) Constraints on the temporal sequencing of neural population activity.
Talks
Marino, P. (2022). Postural and volitional signals modulate separate neural dimensions. Oral Presentation at Neural Control of Movement Annual Meeting.
Marino, P. (2022). Monkeys exhibit a paradoxical performance decrement in high-stakes scenarios. Oral Presentation at Center for the Neural Basis of Cognition Annual Retreat.
Selected Conference Presentations
(* = equal contribution; ** = equal senior author contribution)
Marino, P.J., Bahureksa, L.A., Fisac, C., Oby, E.R., Motiwala, A., Grigsby, E.M., Smoulder, A.L., Degenhart, A.D., Joiner, W.M., Chase, S.M., Yu, B.M., Batista A.P. (2022). Posture and motor signals are organized in primary motor cortex. Poster presentation at the Society for Neuroscience Annual Meeting.
Marino, P.J., Bahureksa, L.A., Fisac, C., Oby, E.R., Motiwala, A., Grigsby, E.M., Smoulder, A.L., Degenhart, A.D., Joiner, W.M., Chase, S.M., Yu, B.M., Batista A.P. (2022). Postural and volitional signals modulate separate neural dimensions. Invited Talk at the Neural Control of Movement Annual Meeting.
Smoulder, A.L., Marino, P.J., Pavlovsky, N.P., Oby, E.R., Snyder, S.E., Bishop, W.E., Yu, B.M., Chase, S.M.**, Batista, A.P.** (2022). Exceptionally large rewards collapse task information in neural population activity. Poster presentation at the Society for Neuroscience Annual Meeting.
Degenhart*, A.D., Grigsby, E.M.*, Oby, E.R.*, Motiwala, A., McClain, N.T., Marino, P.J., Batista, A.P.**, Yu, B.M.** (2022). Constraints on the temporal sequencing of neural population activity. Poster presentation at the Society for Neuroscience Annual Meeting.
Smoulder, A.L., Marino, P.J., Pavlovsky, N.P., Oby, E.R., Snyder, S.E., Bishop, W.E., Yu, B.M., Chase, S.M.**, Batista, A.P.** (2022). Exceptionally large rewards lead to a collapse in neural information about upcoming movements. Poster presentation at Computational and Systems Neuroscience (Cosyne) Meeting.
Marino, P.J., Oby, E.R., Motiwala, A., Grigsby, E.M., Degenhart, A.D., Yu, B.M., Batista, A.P. (2021) The arm’s posture does not alter the time course of population activity in motor cortex. Poster presentation at Computational and Systems Neuroscience (Cosyne) Meeting.
Awards and Honors
Neural Control of Movement Scholarship (2022)
McClelland Prize, Center for the Neural Basis of Cognition, U. of Pittsburgh and Carnegie Mellon University (2022)
Bioengineering Travel Grant, University of Pittsburgh (2022)
Bevier Award, University of Pittsburgh (2018)
National Science Foundation Graduate Research Fellowship Program (2015 - 2018)
Tau Beta Pi Honor society, University of Notre Dame (2013 - 2015)
President’s Scholarship, University of Notre Dame (2010-2015)
Dean’s List, University of Notre Dame (2010 - 2015)
Teaching
Teaching Assistant, Senior Design, University of Texas at Austin (2016 - 2017)
Teaching Assistant, Introduction to Fortran, University of Notre Dame (2014)
Professional Service
Engineering Graduate Student Organization Social Chair, University of Pittsburgh (2015)
Co-founder, Neural Interface Initiative, University of Texas at Austin (2016 - 2018)
President, Tau Beta Pi, University of Notre Dame (2014)
Engineering Commissioner for Alumni Hall, University of Notre Dame (2012)
Contact
You can reach me via email at pmarino162@gmail.com
Also check out my LinkedIn !