Joshua T. Vogelstein
Joshua T. Vogelstein
1980 (age 42–43)
|Alma mater||Washington University in St. Louis|
Johns Hopkins University
|Known for||Connectomics, Graph theory|
|Awards||F1000 Prime Recommended (2014), |
Spotlight, Neural Information Processing Systems (2013),
|Institutions||Johns Hopkins University|
|Thesis||OOPSI: A family of optimal optical spike inference algorithms for inferring neural connectivity from population calcium imaging (2009)|
|Doctoral advisor||Eric Young|
|Other academic advisors||Carey Priebe|
This article contains text that is written in a promotional tone. (October 2023)
A major contributor to this article appears to have a close connection with its subject. (October 2023)
Joshua T. Vogelstein is an American biomedical engineer. He is an Associate Professor of Biomedical Engineering at Johns Hopkins University, where he sits at the Center for Imaging Science. Vogelstein also holds joint appointments in the departments of Applied Mathematics and Statistics, Computer Science, Electrical and Computer Engineering, Biostatistics, and Neuroscience. He has appointments in the Institute for Data Intensive Engineering and Sciences, Institute for Computational Medicine, Kavli Neuroscience Discovery Institute, and the Mathematical Institute for Data Science.
His research focuses primarily on the intersection of natural and artificial intelligence. His group develops and applies high-dimensional nonlinear machine learning methods to biomedical data science challenges. They have published over 100 papers in prominent scientific and engineering journals and conferences including Nature, Science, PNAS, Neurips, and JMLR, with over 10,000 citations and an h-index over 40. They received funding from the Transformative Research Award from NIH, the NSF CAREER award, Microsoft Research, and many other government, for-profit and nonprofit organizations. He has advised over 60 trainees, and taught about 200 students in his eight years as faculty. In addition to his academic work, he co-founded Global Domain Partners, a quantitative hedge fund that was acquired by Mosaic Investment Partners in 2012, and software startup Gigantum, which was acquired by nVidia in early 2022. He is currently the lllChief lllIntelligence lllOfficer for Sensie.
Vogelstein did his undergraduate studies at McKelvey School of Engineering at Washington University in St. Louis, where he received his Bachelor of Science degree in biomedical engineering in 2002. From 2003 to 2009 he studied at Johns Hopkins University, where he received his Master of Science in applied mathematics and statistics and a Ph.D. in neuroscience from the Johns Hopkins School of Medicine, where he developed algorithms for spike detection in calcium imaging.
From 2014 to 2018, Vogelstein was the director of undergraduate studies for the Institute for Computational Medicine. He has also held positions as an endeavor scientist at the Child Mind Institute, a senior research scientist for the departments of statistical sciences and mathematics and neurobiology at Johns Hopkins University, and as affiliated faculty at Duke University.
Vogelstein's research focuses on understanding how massive biomedical datasets are best analyzed to discover new knowledge about the function of living systems in health and disease, and how this knowledge can be harnessed to provide improved, more affordable health care. Specifically, his work often focuses on big and wide data in neuroscience, and in particular on the statistics of brain graphs and connectomics.
Open Science, Open Data
Joshua Vogelstein founded and directs the NeuroData lab, which has created an ecosystem of open-source tools for neuroscientists and hosts a collection of open-source data.
Network Statistics and Connectomics
One of Vogelstein's current areas of study is connectal coding, an emerging field focusing on the study of how brain structure, rather than brain activity, encodes information; this represents a shift from the traditional study of neural coding. Some of his notable work in this area includes the analysis of the first connectome of an insect brain (that of a Drosophila larva) and his use of machine learning techniques to reveal patterns in larval Drosophila behaviors.
Motivated by this work on connectomes, Vogelstein has also developed statistical and computational methods for networks, including network statistical models, network embedding methods, and methods for comparing and matching networks.
Dr. Vogelstein studies various out-of-distribution learning paradigms including meta, transfer, lifelong or continual learning, prospective learning both theoretically and practically. Motivated from his insight from brain study, he aims at making artificial intelligence better, more natural and complementary to human intelligence.
Vogelstein's research use domain knowledge from the fields of neuroscience and machine learning synergistically, aiming to gain deeper insights into natural intelligences (including organisms with brain) as well as building more robust and flexible artificial intelligences. Some key attributes of intelligence that he has researched on include representation capacity and learning efficiency.
Joshua Vogelstein has been on the advisory board for numerous commercial companies, including Gigantum, Mind-X, and PivotalPath. Vogelstein has also held the position of Chief Data Scientist at Global Domain Partners, LLC. He is currently the Chief Intelligence Officer for Sensie. He works extensively with Microsoft Research.
- "NeuroData Awards".
- Vogelstein, Joshua T.; Perlman, Eric; Falk, Benjamin; Baden, Alex; Gray Roncal, William; Chandrashekhar, Vikram; Collman, Forrest; Seshamani, Sharmishtaa; Patsolic, Jesse L.; Lillaney, Kunal; Kazhdan, Michael; Hider, Robert; Pryor, Derek; Matelsky, Jordan; Gion, Timothy; Manavalan, Priya; Wester, Brock; Chevillet, Mark; Trautman, Eric T.; Khairy, Khaled; Bridgeford, Eric; Kleissas, Dean M.; Tward, Daniel J.; Crow, Ailey K.; Hsueh, Brian; Wright, Matthew A.; Miller, Michael I.; Smith, Stephen J.; Vogelstein, R. Jacob; et al. (2019). "A community-developed open-source computational ecosystem for big neuro data". Nature Methods. 15 (11): 846–847. arXiv:1804.02835. doi:10.1038/s41592-018-0181-1. PMC 6481161. PMID 30377345.
- Vogelstein, Joshua T; Bridgeford, Eric W; Pedigo, Benjamin D; Chung, Jaewon; Levin, Keith; Mensh, Brett; Priebe, Carey E (2019-04-01). "Connectal coding: discovering the structures linking cognitive phenotypes to individual histories". Current Opinion in Neurobiology. Machine Learning, Big Data, and Neuroscience. 55: 199–212. doi:10.1016/j.conb.2019.04.005. ISSN 0959-4388. PMID 31102987. Retrieved 2019-09-22.
- Winding, Michael; Pedigo, Benjamin D.; Barnes, Christopher L.; Patsolic, Heather G.; Park, Youngser; Kazimiers, Tom; Fushiki, Akira; Andrade, Ingrid V.; Khandelwal, Avinash; Valdes-Aleman, Javier; Li, Feng; Randel, Nadine; Barsotti, Elizabeth; Correia, Ana; Fetter, Richard D.; Hartenstein, Volker; Priebe, Carey E.; Vogelstein, Joshua T.; Cardona, Albert; Zlatic, Marta (2023-03-10). "The connectome of an insect brain". Science. 379 (6636): –9330. doi:10.1126/science.add9330. PMC 7614541. PMID 36893230. S2CID 254070919.
- Vogelstein, Joshua T.; Park, Youngser; Ohyama, Tomoko; Kerr, Rex A.; Truman, James W.; Priebe, Carey E.; Zlatic, Marta (2014-04-25). "Discovery of Brainwide Neural-Behavioral Maps via Multiscale Unsupervised Structure Learning". Science. 344 (6182): 386–392. Bibcode:2014Sci...344..386V. doi:10.1126/science.1250298. ISSN 0036-8075. PMID 24674869. S2CID 7404747.
- Zeng, Hongkui (2018). "Mesoscale Connectomics". Current Opinion in Neurobiology. 50: 154–162. doi:10.1016/j.conb.2018.03.003. ISSN 0959-4388. PMC 6027632. PMID 29579713.
- Athey, Thomas L.; Tward, Daniel J.; Mueller, Ulrich; Vogelstein, Joshua T.; Miller, Michael I. (2022-04-25). "Hidden Markov modeling for maximum probability neuron reconstruction". Communications Biology. 5 (1): 388. doi:10.1038/s42003-022-03320-0. ISSN 2399-3642. PMC 9038756. PMID 35468989.
- Athey, Thomas L.; Wright, Matthew A.; Pavlovic, Marija; Chandrashekhar, Vikram; Deisseroth, Karl; Miller, Michael I.; Vogelstein, Joshua T. (2023-03-01), "BrainLine: An Open Pipeline for Connectivity Analysis of Heterogeneous Whole-Brain Fluorescence Volumes", BioRxiv: The Preprint Server for Biology, bioRxiv, doi:10.1101/2023.02.28.530429, PMC 10002688, PMID 36909631, retrieved 2023-03-28
- Athreya, Avanti; Fishkind, Donniell E.; Tang, Minh; Priebe, Carey E.; Park, Youngser; Vogelstein, Joshua T.; Levin, Keith; Lyzinski, Vince; Qin, Yichen; Sussman, Daniel L. (2018). "Statistical Inference on Random Dot Product Graphs: a Survey". Journal of Machine Learning Research. 18 (226): 1–92. arXiv:1709.05454. ISSN 1533-7928. Retrieved 2022-08-02.
- Arroyo, Jesús; Athreya, Avanti; Cape, Joshua; Chen, Guodong; Priebe, Carey E.; Vogelstein, Joshua T. (2021). "Inference for Multiple Heterogeneous Networks with a Common Invariant Subspace". Journal of Machine Learning Research. 22 (142): 1–49. arXiv:1906.10026. ISSN 1533-7928. PMC 8513708. PMID 34650343. Retrieved 2023-03-28.
- Binkiewicz, N.; Vogelstein, J. T.; Rohe, K. (2017). "Covariate-assisted spectral clustering". Biometrika. 104 (2): 361–377. doi:10.1093/biomet/asx008. ISSN 1464-3510. PMC 5793492. PMID 29430032.
- Koutra, Danai; Vogelstein, Joshua T.; Faloutsos, Christos (2013-05-02). "DeltaCon: A Principled Massive-Graph Similarity Function". Proceedings of the 2013 SIAM International Conference on Data Mining (SDM). Society for Industrial and Applied Mathematics. pp. 162–170. arXiv:1304.4657. doi:10.1137/1.9781611972832.18. ISBN 978-1-61197-262-7. S2CID 5310840. Retrieved 2023-03-28.
- Vogelstein, Joshua T.; Conroy, John M.; Lyzinski, Vince; Podrazik, Louis J.; Kratzer, Steven G.; Harley, Eric T.; Fishkind, Donniell E.; Vogelstein, R. Jacob; Priebe, Carey E. (2015). "Fast Approximate Quadratic programming for graph matching". PLOS ONE. 10 (4): e0121002. Bibcode:2015PLoSO..1021002V. doi:10.1371/journal.pone.0121002. ISSN 1932-6203. PMC 4401723. PMID 25886624.
- Wang, Qingyang; Powell, Michael A.; Geisa, Ali; Bridgeford, Eric; Priebe, Carey E.; Vogelstein, Joshua T. (2023-03-08). "Why do networks have inhibitory/negative connections?". arXiv:2208.03211 [cs.LG].
- Wang, Qingyang; Powell, Michael A.; Geisa, Ali; Bridgeford, Eric; Vogelstein, Joshua T. (2023-03-29). "Polarity is all you need to learn and transfer faster". arXiv:2303.17589 [cs.LG].
- "global domain partners". Bloomberg News. 22 September 2023.