Mike Procopio

(Michael J. Procopio)

Software Engineer and Machine Learning Researcher

Background

I'm a Machine Learning researcher and Software Engineer at Google in Boulder, Colorado. I currently work on Google Docs, developing features such as file versions, drag and drop upload, and folder upload. Interested in working for Google? Have a look at current job openings!

I received my Ph.D. in Machine Learning from the Computer Science Department at the University of Colorado at Boulder in 2007. (Here's an article that summarizes my doctoral research.) My research interests include machine learning classification and ensemble methods, computer vision, robotics, and search. I also like to dabble in this and that, e.g., Braitenberg Vehicles.

My resume (PDF).

Information and downloads for the Hand-Labeled DARPA LAGR Datasets.

I can be contacted through my LinkedIn profile or at mprocopio@gmail.com.

Selected Publications  (view in Google Scholar)

Estimation of arrival times from seismic waves: a manifold-based approach

Kye M. Taylor, Michael J. Procopio, Christopher J. Young, and Francois G. Meyer
Geophysical Journal International (GJI) Seismology, 2011

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

Michael J. Procopio, Jane Mulligan, and Greg Grudic
International Conference on Robotics and Automation (ICRA), 2010

SAPLE: Sandia Advanced Personnel Locator Engine

Michael J. Procopio
Sandia National Laboratories Technical Report #SAND2010-1756, 2010
Thumbnail
not available

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

Generalized BadRank with Graduated Trust

Tamara G. Kolda and Michael J. Procopio
Sandia National Laboratories Technical Report #SAND2009-6670, 2009

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

Michael J. Procopio, W. Philip Kegelmeyer, Greg Grudic, and Jane Mulligan
Multiple Classifier Systems (MCS), 2009

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
31st Monitoring Research Review (MRR): Ground-Based Nuclear Explosion Monitoring Technologies, 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
31st Monitoring Research Review (MRR): Ground-Based Nuclear Explosion Monitoring Technologies, 2009

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

Michael J. Procopio, Jane Mulligan, and Greg Grudic
Journal of Field Robotics (JFR), 2009

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

Michael J. Procopio, Jane Mulligan, and Greg Grudic
International Conference on Intelligent Robots and Systems (IROS), 2008

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

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

Michael J. Procopio, Jane Mulligan, and Greg Grudic
International Conference on Intelligent Robots and System (IROS 2007)

Using Binary Classifiers to Augment Stereo Vision for Enhanced Autonomous Robot Navigation

Michael J. Procopio, Thomas Strohmann, Adam R. Bates, Greg Grudic, and Jane Mulligan.
University of Colorado at Boulder Technical Report, April 2007

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
International ACM SIGGROUP Conference on Supporting Group Work (GROUP 2005)

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

Michael J. Procopio.
Master of Science Thesis, University of Florida, 2002.