Background

I'm a Senior Staff Software Engineer and AI / Machine Learning researcher at Google on the AppSheet team. I completed an engineering residency with Gradient Ventures supporting test.ai and myst.ai.

Previously, I worked on Google Drive for an eight-year tenure serving as the Tech Lead / Manager (TLM) for both the Google Drive Intelligence team (leading the Quick Access and Priority features) and the Google Drive API team (leading the Drive API and the WhatsApp / Drive integration).

Prior to that, I worked on Google Drive more generally developing features such as file versions, simplified drag and drop upload, the Google Drive API (including Version 2 of the API), Apps in Google Drive, Apps for Gmail Attachments, Google My Maps in Drive, and Android Auto Backup in Drive.

On AppSheet, I published an article on the Apps Script connector for AppSheet, which brings the power of Apps Script's low-code platform and API integrations to AppSheet:
Announcing the Apps Script connector for AppSheet: Automate workflows for Google Workspace

I also wrote an article on AppSheet Dynamic Email that highlights the power of no-code platforms to build apps that integrate with Gmail: Bring no-code apps to your Gmail inbox. Here’s how

Research

I received my Ph.D. in Machine Learning from the University of Colorado at Boulder. My research interests include machine learning classification and regression through deep learning and ensemble methods, autonomous vehicles, recommendation systems, computer vision, and robotics. As part of my doctoral research, I published the Hand-Labeled DARPA LAGR Datasets (also available on Kaggle).

Presentations

Publications

View publications in Google Scholar.

False Event Screening Using Data Mining in Historical Archives

Timothy J. Draelos, Michael J. Procopio, Jennifer E. Lewis, and Christopher J. Young
BibTeX
@article{Draelos-SRL-12,
  author = {Timothy J. Draelos and Michael J. Procopio and Jennifer E. Lewis and Christopher J. Young},
  title = {False Event Screening Using Data Mining in Historical Archives},
  journal = {Seismological Research Letters},
  volume = {83},
  number = {2},
  pages = {267--274},
  year = {2012},
  doi = {10.1785/gssrl.83.2.267}
}

Estimation of Arrival Times from Seismic Waves: a Manifold-Based Approach

Kye M. Taylor, Michael J. Procopio, Christopher J. Young, and Francois G. Meyer
BibTeX
@article{Taylor-GJI-11,
  author = {Kye M. Taylor and Michael J. Procopio and Christopher J. Young and Francois G. Meyer},
  title = {Estimation of arrival times from seismic waves: a manifold-based approach},
  journal = {Geophysical Journal International},
  volume = {185},
  number = {1},
  pages = {435--452},
  year = {2011},
  doi = {10.1111/j.1365-246X.2011.04947.x}
}

Coping with Imbalanced Training Data for Improved Terrain Prediction in Autonomous Outdoor Robot Navigation

Michael J. Procopio, Jane Mulligan, and Greg Grudic
BibTeX
@inproceedings{Procopio-ICRA-10,
  author = {Michael J. Procopio and Jane Mulligan and Greg Grudic},
  title = {Coping with Imbalanced Training Data for Improved Terrain Prediction in Autonomous Outdoor Robot Navigation},
  booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
  pages= {518--525},
  location = {Anchorage, AK},
  month = {May},
  year = {2010},
  doi={10.1109/ROBOT.2010.5509634}
}

Image Data Processing for Integrated Circuit Analysis

Kurt W. Larson, Michael J. Procopio, Antonio I. Gonzales, David M. Melgaard, Fred Rothganger, Daniel S. Myers, and Brandon R. Rohrer
Sandia National Laboratories Technical Report #SAND2009-8404, 2009
Full text not available
BibTeX
@techreport{Larson-SAND2009-8404,
  author = {Kurt W. Larson and Michael J. Procopio and Antonio I. Gonzales and David M. Melgaard and Fred Rothganger and Daniel S. Myers and Brandon R. Rohrer},
  title = {Image Data Processing for Integrated Circuit Analysis},
  institution = {Sandia National Laboratories, Albuquerque, NM},
  number = {SAND2009-8404},
  year = {2009}
}

Generalized BadRank with Graduated Trust

Tamara G. Kolda and Michael J. Procopio
Sandia National Laboratories Technical Report #SAND2009-6670, 2009
BibTeX
@techreport{Kolda-SAND2009-6670,
  author = {Tamara G. Kolda and Michael J. Procopio},
  title = {Generalized BadRank with Graduated Trust},
  institution = {Sandia National Laboratories, Albuquerque, NM and Livermore, CA},
  number = {SAND2009-6670},
  month = {October},
  year = {2009}
}

Terrain Segmentation with On-line Mixtures of Experts for Autonomous Robot Navigation

Michael J. Procopio, W. Philip Kegelmeyer, Greg Grudic, and Jane Mulligan
BibTeX
@inproceedings{Procopio-MCS-09,
  author = {Michael J. Procopio and W. Philip Kegelmeyer and Greg Grudic and Jane Mulligan},
  title = {Terrain Segmentation with On-Line Mixtures of Experts for Autonomous Robot Navigation},
  booktitle = {Multiple Classifier Systems},
  pages = {385--397},
  location = {Reykjavik, Iceland},
  month = {June},
  year = {2009},
  doi = {10.1007/978-3-642-02326-2_39},
  series = {Lecture Notes in Computer Science (LNCS)},
  volume = {5519},
  editor = {Jon Atli Benediktsson and Josef Kittler and Fabio Roli},
  publisher = {Springer}
}

Using machine learning to improve the efficiency and effectiveness of automatic nuclear explosion monitoring systems

Michael J. Procopio, Christopher J. Young, and Jennifer E. Lewis
BibTeX
@inproceedings{Procopio-MRR-09,
  author = {Michael J. Procopio and Christopher J. Young and Jennifer E. Lewis},
  title = {Using Machine Learning to Improve the Efficiency and Effectiveness of Automatic Nuclear Explosion Monitoring Systems},
  booktitle = {2009 Monitoring Research Review: Ground-Based Nuclear Explosion Monitoring Technologies},
  pages = {788--797},
  location = {Tucson, AZ},
  month = {September},
  year = {2009}
}

Exploring the limits of waveform correlation event detection as applied to the 1994 Northridge earthquake aftershock sequence

Dorthe B. Carr, Megan E. Resor, Christopher J. Young, and Michael J. Procopio
BibTeX
@inproceedings{Carr-MRR-09,
  author = {Dorthe B. Carr and Megan E. Resor and Christopher J. Young and Michael J. Procopio},
  title = {Exploring the limits of waveform correlation event detection as applied to the 1994 Northridge earthquake aftershock sequence},
  booktitle = {2009 Monitoring Research Review: Ground-Based Nuclear Explosion Monitoring Technologies},
  pages = {303--312},
  location = {Tucson, AZ},
  month = {September},
  year = {2009}
}

Learning Terrain Segmentation with Classifier Ensembles for Autonomous Robot Navigation in Unstructured Environments

Michael J. Procopio, Jane Mulligan, and Greg Grudic
BibTeX
@article{Procopio-JFR-09,
  author = {Michael J. Procopio and Jane Mulligan and Greg Grudic},
  title = {Learning Terrain Segmentation with Classifier Ensembles for Autonomous Robot Navigation in Unstructured Environments},
  journal = {Journal of Field Robotics},
  volume = {26},
  number = {2},
  pages = {145--175},
  year = {2009},
  publisher = {Wiley Periodicals, Inc.},
  address = {Hoboken, NJ},
  doi = {10.1002/rob.20279}
}

Learning in Dynamic Environments with Ensemble Selection for Autonomous Outdoor Robot Navigation

Michael J. Procopio, Jane Mulligan, and Greg Grudic
BibTeX
@inproceedings{Procopio-IROS-08,
  author = {Michael J. Procopio and Jane Mulligan and Greg Grudic},
  title = {Learning in Dynamic Environments with \emph{{E}nsemble {S}election} for Autonomous Outdoor Robot Navigation},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages = {620--627},
  location = {Nice, France},
  month = {September},
  year = {2008},
  doi = {10.1109/IROS.2008.4651215}
}

An Experimental Analysis of Classifier Ensembles for Learning Drifting Concepts Over Time in Autonomous Outdoor Robot Navigation

Michael J. Procopio
Ph.D. Thesis, University of Colorado at Boulder, 2007
BibTeX
@phdthesis{Procopio-PhdThesis-07,
  author = {Michael J. Procopio},
  title = {An Experimental Analysis of Classifier Ensembles for Learning Drifting Concepts Over Time in Autonomous Outdoor Robot Navigation},
  school = {University of Colorado at Boulder},
  year = {2007},
  month = {December},
  address = {Boulder, CO}
}

Long-Term Learning Using Multiple Models for Outdoor Autonomous Robot Navigation

Michael J. Procopio, Jane Mulligan, and Greg Grudic
BibTeX
@inproceedings{Procopio-IROS-07,
  author = {Michael J. Procopio and Jane Mulligan and Greg Grudic},
  title = {Long-Term Learning Using Multiple Models for Outdoor Autonomous Robot Navigation},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  pages= {3158--3165},
  location = {San Diego, CA},
  month = {October},
  year = {2007},
  doi={10.1109/IROS.2007.4399583}
}

Benefits of Synchronous Collaboration Support for an Application-Centered Analysis Team Working on Complex Problems: a Case Study

John M. Linebarger, Andrew J. Scholand, Mark Ehlen, and Michael J. Procopio
BibTeX
@inproceedings{Linebarger-GROUP-05,
  author = {John M. Linebarger and Andrew J. Scholand and Mark A. Ehlen and Michael J. Procopio},
  title = {Benefits of synchronous collaboration support for an application-centered analysis team working on complex problems: a case study},
  booktitle = {Proceedings of the International ACM SIGGROUP Conference on Supporting Group Work},
  year = {2005},
  pages = {51--60},
  location = {Sanibel Island, FL},
  doi = {10.1145/1099203.1099211}
}

YCab.NET: Decentralized Collaboration Groupware for Mobile Devices using the Microsoft .NET Framework

Michael J. Procopio
BibTeX
@mastersthesis{Procopio-MastersThesis-02,
  author = {Michael J. Procopio},
  title = {YCab.NET: Decentralized Collaboration Groupware for Mobile Devices using the Microsoft .NET Framework},
  school = {University of Florida},
  year = {2002},
  month = {May},
  address = {Gainesville, FL},
  url = {https://ufdc.ufl.edu/UFE1000155/00001}
}

Patents

View in google patents

42 inventions with granted patents and one published patent application, with related U.S. and international filings grouped below.

System and method for automatic cloud-based full-data backup and restore on mobile devices

Michael Jeffrey Procopio, Christiaan Prins, Ramesh Nagarajan, Ushasree Kode, Christopher Tate, Di Wu, Reuben Kan, and John Herndon
U.S. Patent 10,455,015 | U.S. Serial No. 15/156,539 | Publication US20160352827A1