I am a PhD candidate in the Department of Psychology at Yale University (Neuroscience track) supported by a NSF GRFP. I primarily work with Nick Turk-Browne. I also work with the Krishnaswamy Lab in the Department of Computer Science and Department of Genetics at Yale and BJ Casey. My work lies at the intersection of human and machine learning. I am interested in the computational principles of human brain activity that enable and constrain learning new skills, and manipulating those to facillitate more efficient learning. I also develop and apply novel analysis techniques to explore individual differences in neuroimaging phenotypes and their relation to behavior and mental health. I completed my undergraduate degree in Cognitive Science, Computer Science, and Spanish at Dartmouth College in winter of 2020, where I worked with Jim Haxby and Caroline Robertson.
Research
Publications, Conference Proceedings, and Preprints
Busch, E.L.*, Conley, M.I.*, & Baskin-Sommers, A. (2024) Manifold Learning Uncovers Nonlinear Interactions between the Adolescent Brain and the Social Environment in Predicting Mental Health Problems. bioRxiv,. Preprint
Busch, E.L., Rapuano, K.M., Anderson, K.M., Rosenberg, M.D., Watts, R., Casey, BJ, Haxby, J.V., & Feilong, M. (2024). Dissociation of reliability, heritability, and predictivity in coarse- and fine-scale functional connectomes during development. Journal of Neuroscience, 44 (6). Paper | Code
Busch, E.L., Rapuano, K.M., Anderson, K.M., Rosenberg, M.D., Watts, R., Casey, BJ, Haxby, J.V., & Feilong, M. (2024). Dissociation of reliability, heritability, and predictivity in coarse- and fine-scale functional connectomes during development. Journal of Neuroscience, 44 (6). Paper | Code
Busch, E.L., Yates, T.S., Turk-Browne, N.B. (2023). Tasks constrain the intrinsic dimensionality of activity in non-selective cortex. Proceedings of the 7th Annual Conference on Cognitive Computational Neuroscience, Paper.
Busch, E.L., Huang, J., Benz, A., Wallenstein, T., Lajoie, G., Wolf, G., Krishnaswamy, S.*, & Turk-Browne, N.B.* (2023). Multi-view manifold learning of human brain-state trajectories. Nature Computational Science, 3, 240-253. Paper | Research Briefing | Analysis Code | T-PHATE Software.
Huang, J.*, Busch, E.L.*, Wallenstein, T.*, Gerasimiuk, M., Benz, A., Lajoie, G., Wolf, G., Turk-Browne, N.B., Krishnaswamy, S. (2022). Learning shared neural manifolds from multi-subject FMRI data. 32nd IEEE Machine Learning for Signal Processing [MLSP 2022] arXiv
Busch, E.L.*, Slipski, L.*, Feilong, M., Guntupalli, J.S., Visconti di Oleggio Castello, M., Huckins, J.F., Nastase, S.A., Gobbini, M.I.,Wager, T.D., Haxby, J.V. (2021). Hybrid hyperalignment: A single high-dimensional model of shared information embedded in cortical patterns of response and functional connectivity. NeuroImage, 233, 117975. Paper | Code
Select posters & presentations (2022-Present)
Posters
Busch, E.L., Conley, M.I., Baskin-Sommers, A., (2024). Using manifold learning to uncover the embedded brain and implications for mental health in youth. Accepted at the Organization for Human Brain Mapping Annual Meeting. Seoul, South Korea.
Busch, E.L., Fincke, E.C., Lajoie, G., Krishnaswamy, S., Turk-Browne, N.B., (2024). Learning on the manifold of human brain activity through real-time neurofeedback. Accepted at the Organization for Human Brain Mapping Annual Meeting. Seoul, South Korea.
Busch, E.L., Yates, T.S., Turk-Browne, N.B., (2023). Tasks constrain the intrinsic dimensionality of activity in non-selective cortex. 7th Annual Conference on Cognitive Computational Neuroscience. Oxford, United Kingdom.
Busch, E.L., Bhaskar, D., Letrou, A., Zhang, X., Noah, J.A., Lajoie, G., Hirsch, J., Turk-Browne, N.B., Krishnaswamy, S. (2022). An encoder-decoder framework for cross-modal translation of brain imaging data. Montreal AI-Neuroscience Meeting. Montreal, Quebec, Canada.
Busch, E.L., Letrou, A., Huang, J., Lajoie, G., Wolf, G., Krishnaswamy, S., & Turk-Browne, N.B. (2022). A neural manifold learning framework for real-time fMRI neurofeedback. Real-time Functional Imaging and Neurofeedback Meeting. New Haven, Connecticut.
Busch, E.L., Rapuano, K.M., Anderson, K.M., Rosenberg, M.D., Watts, R., Casey, BJ, Haxby, J.V., & Feilong, M. (2022). Heritable template underlies reliable idiosyncrasies in the developing fine-scale connectome. Organization for Human Brain Mapping Annual Meeting. Glasgow, Scotland.
Letrou, A., Busch, E.L., & Turk-Browne, N.B., (2022). Relating neural dynamics and emotion dynamics with nonlinear manifold learning. Social and Affective Neurosience Society Annual Meeting.Virtual.
Select talks
Dissociable scales reflect reliable, heritable, and behaviorally-relevant individual differences in the developing connectome. (March 2024) ABCD Innovations and Insights Meeting. NIH Campus.
Learning on the manifold of human brain activity via real-time neurofeedback. (November 2023) Nanosymposium on Neural Decoding and Neuroprosthetics. Society for Neuroscience Annual Meeting, Washington D.C.
Multi-view manifold learning of human brain-state trajectories. (April 2023) Shine Lab Meeting, University of Sydney.
An encoder-decoder framework for cross-modal translation of brain imaging data. (December 2022) MAIN 2022 Conference Lightning Talk.
The LEGO theory of the developing functional connectome. (September 2022) ABCD Imaging Analytics Working Group.
Modern fMRI analysis techniques. Guest Lecture, Yale NSCI 270 November 2021.
Hyperalignment: Foundations, flavors, and functions. (April 2021) FINN Lab Meeting, Dartmouth College.