Dominic M. Mazzoni
1210 Walleye Cmn
Fremont, CA 94536
Objective:I'm currently happily employed. Thanks for your interest!
M.S. in Computer Science, Carnegie Mellon University, Pittsburgh, PA, 2003
Studied computer architecture, type systems for programming languages, advanced algorithms, advanced A.I., computer networking, speech recognition, and digital audio. Developed algorithms for fast disk-based audio editing. Researched melody matching algorithms and developed (in C++ on Linux) a working prototype of a melody-based music retrieval tool.
B.S. in Mathematics, Harvey Mudd College, Claremont, CA, 1999
Studied combinatorics, number theory, graph theory, probability, algorithms, computability theory, programming languages, and computational linguistics. Researched network routing algorithms for high-speed networks of workstations.
Software Engineer, Google, Inc., Santa Monica, CA, 2006+
Worked on products including AdSense and Google Audio Ads, developed machine learning infrastructure and back-end server code in C++, Python, and Java.
Research Programmer, NASA Jet Propulsion Laboratory, Pasadena, CA, 2001 - 2006
- Did pure machine learning research in collaboration with other computer scientists, leading to several advances in support vector machine (SVM) theory and practice.
- Co-developed a custom SVM library that's twice as fast as any existing implementation (for certain types of scientific data sets).
- Developed SVM-based scene classifier for the EO-1 spacecraft that was part of the 2005 NASA Software of the Year winner, the Autonomous Sciencecraft Experiment.
- Developed SVM-based scene classifier for the MISR satellite instrument, which has been running operationally since December 1, 2005, and has classified 35 billion pixels so far.
- Created innovative PixelLearn software, which uses cutting-edge SVMs and active learning to enable scientists to label the pixels in a hyperspectral, multi-source image for machine learning classification.
- Maintained a 16-machine Beowulf cluster and developed parallel machine learning algorithms
- Collaborated with geologists and atmospheric scientists to develop custom tools integrating the latest cutting-edge machine learning technology into increasing science return from NASA missions.
Project leader, Audacity, 1999+
- Original author and currenly still a lead developer (in my "spare time") of Audacity, the most popular audio editor in the world. Over 15 million downloads as of December 2006, available in 30+ languages.
- Contributed over 100,000 lines of code over the years.
- Contributed custom code for Windows, Mac OS 9, Mac OS X, and Linux, plus mostly cross-platform code using wxWidgets.
- Helped to build and maintain dynamic website and translation system, with 20+ languages and dozens of translation contributors.
- Led a team of 4-6 active developers and dozens of contributors, plus documentation writers, translation writers, and graphics artists, to release two major versions of Audacity and more than a dozen minor updates and beta releases. Coordinated the simultaneous release of Windows, Mac, and Linux versions of every single version of Audacity, with no significant missing features on any platform, ever.
- Technologies used included: cross-platform GUI programming, multithreaded programming and thread synchronization, audio filtering and processing, real-time audio/video synchronization, advanced algorithms and data structures (editing of 1 GB+ data files with no perceptible user delay on an ordinary PC), unit testing, CVS.
Research and Teaching Assistant, Carnegie Mellon University, Pittsburgh, PA, 1999 - 2001.
- Started developing Audacity (see above)
- Developed working "query by humming" system for music information retrieval
- Teaching assistant for two courses, Discrete Mathematics and Introductory Computer Programming, including weekly recitations, designing homework problems and exam problems, and giving about six lectures to 300 students.
Software Developer, Horizon, a Glimpse of Tomorrow, Inc., Pasadena, CA, Summer 1999 and Summer 2000.
Software Developer Intern, Myricom, Inc., Arcadia, CA, Summer 1998
Worked with their network simulator, a C++ program with a Java (Swing) front-end, that ran on Linux, Solaris, and Windows NT. Added new features to the simulator and the front-end, and researched new routing algorithms.
Software Developer Intern, RealNetworks, Seattle, WA, Summer 1996
Worked in a team of about five to add features to the free RealAudio Player, resulting in the first RealAudio Player Plus, a shrink-wrap product for Windows and Macintosh. Used C and C++ for development, and CVS for revision control. Individually wrote a new installer for RealAudio on the Macintosh and ported an initial prototype of RealVideo to the Macintosh.
Significant experience developing client-side applications for Linux, Mac OS X, and Windows. Experience developing web-based client/server applications on Linux using Apache.
ACM International Collegiate Programming Contest
1st place in 1998 and 3rd place in 1999 in regional (multi-state) finals of the contest. Used C and C++ in teams of 3, competing against about 50 other teams.
NASA Software of the Year, 2005
Autonomous Sciencecraft Experiment. One part-time developer on a team of more than 15.
- Kiri Wagstaff, Michael Kocurek, Dominic Mazzoni, and Benyang Tang. Progressive Refinement for Support Vector Machines. Data Mining and Knowledge Discovery, 2009 (in press).
- Dominic Mazzoni, Michael J. Garay, Roger Davies, David Nelson. An operational MISR pixel classifier using support vector machines. Remote Sensing of Environment 107 (2007), 149 - 158.
- Dominic Mazzoni, Jennifer A. Logan, David Diner, Ralph Kahn, Lingling Tong, Qinbin Li. A data-mining approach to associating MISR smoke plume heights with MODIS fire measurements. Remote Sensing of Environment 107 (2007), 138 - 148.
- Yuekui Yang, Larry Di Girolamo, Dominic Mazzoni. Selection of the automated thresholding algorithm for the Multi-angle Imaging SpectroRadiometer Radiometric Camera-by-Camera Cloud Mask over land. Remote Sensing of Environment 107 (2007), 159-171.
- Dominic Mazzoni, Kiri L. Wagstaff, and Michael Burl. Active Learning with Irrelevant Examples. Proc. of the 17th European Conference on Machine Learning, September 2006.
- Rebecca Castano, Dominic Mazzoni, Nghia Tang, Ron Greeley, Thomas Doggett, Benjamin Cichy, Steve Chien, and Ashley Davies. Learning Classifiers for Science Event Detection on a Remote Sensing Spacecraft. Proc. 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2006, pp. 845-851.
- Benyang Tang and Dominic Mazzoni. Multiclass Reduced-set Support Vector Machines. Proceedings of the 2006 International Conference on Machine Learning (ICML-06), June 2006, pp. 115-122.
- Michael C. Burl, Dennis DeCoste, Brian L. Enke, Dominic Mazzoni, William J. Merline, Lucas Scharenboich. Automated Knowledge Discovery from Simulators. Proceedings of the Sixth SIAM International Conference on Data Mining, April 2006.
- Rebecca Castano, Dominic Mazzoni, Nghia Tang, Thomas Doggett, Steve Chien, Ronald Greeley, Ben Cichy, and Ashley Davies. Learning Classifiers for Science Event Detection in Remote Sensing Imagery. iSAIRAS, Sept 2005.
- Dominic Mazzoni, Ákos Horváth, Michael J. Garay, Benyang Tang, and Roger Davies. A MISR cloud-type classifier using reduced Support Vector Machines. Proceedings of the Eighth Workshop on Mining Scientific and Engineering Datasets, 2005 SIAM International Conference on Data Mining.
- Dominic Mazzoni. LibFeature: A software library for quickly generating feature vectors on the fly from structured data. Proceedings of the Eighth Workshop on Mining Scientific and Engineering Datasets, 2005 SIAM International Conference on Data Mining.
- Michael J. Garay, Dominic Mazzoni, Roger Davies, and Dave Diner. The application of Support Vector Machines to the Analysis of Global Datasets from MISR. Proceedings of the Fourth Conference on Artificial Intelligence Applications to Environmental Sciences, American Meteorological Society, San Diego, CA, January 2005.
- Dennis DeCoste and Dominic Mazzoni. Fast Query-Optimized Kernel Machine Classification Via Incremental Approximate Nearest Support Vectors. Proceedings of the 2003 International Conference on Machine Learning (ICML-03), August 2003, pp. 115-122.
- Dominic Mazzoni and Roger Dannenberg. A Fast Data Structure for Disk-Based Audio Editing. Computer Music Journal, Volume 26, No. 2, 2002, pp. 62-76.
- Birmingham, Dannenberg, Wakefield, Bartsch, Bykowski, Mazzoni, Meek, Mellody, and Rand. MUSART: Music Retrieval via Aural Queries, in ISMIR 2001 2nd Annual International Symposium on Music Information Retrieval, Bloomington: Indiana University, (2001), pp. 73-82.
- Dominic Mazzoni and Roger Dannenberg. Melody Matching Directly from Audio. Two-page summary of technical report. Proceedings of the 2001 International Symposium on Music Information Retrieval.
- Dominic Mazzoni and Roger Dannenberg. A Fast Data Structure for Disk-Based Audio Editing. (Condensed.) Proceedings of the 2001 International Computer Music Conference, International Computer Music Association, (September 2001), pp. 107-110.
- Ran Libeskind-Hadas, Dominic Mazzoni, and Ranjith Rajagopalan. Optimal Contention-Free Unicast-Based Multicast in Switch-Based Networks of Workstations. Proceedings of the 1998 12th International Parallel Processing Symposium and 9th Symposium on Parallel and Distributed Processing (IPPS/SPDP), pp. 358-364.
- Ran Libeskind-Hadas, Dominic Mazzoni, and Ranjith Rajagopalan. Tree-Based Multicasting in Wormhole-Routed Irregular Topologies. Proceedings of the 1998 IPPS/SPDP, pp. 244-249.
Other works and publications:
- Men, Interrupted (independent film). Jonathan Stokes, director. Dominic Mazzoni, composer. 2009: http://www.imdb.com/title/tt1470666/
- The Last Hurrah (independent film). Jonathan Stokes, director. Dominic Mazzoni, composer. 2009: http://www.imdb.com/title/tt1078904/
- Dominic Mazzoni and Scott Granneman. Podcasting with Audacity: Creating a Podcast with Free Audio Software (book). Prentice Hall, 2007.
- Lucas Scharenbroich, T. Doggett, T. Kratz, R. Castano, S. Chien, A. G. Davies, D. Tran, and Dominic Mazzoni. Cryosphere Sensor Webs With The Autonomous Sciencecraft Experiment. Eos Trans. AGU, 87 (52), Fall Meet. Suppl., Abstract IN53A-0816, 2006.
- Mike Kocurek, K. Wagstaff, D. Mazzoni, S. Sain, L. Scharenbroich, and T. M. Stough. Fast, Interactive Analysis of Remote Sensing Data with the HARVIST System. Eos Trans. AGU, 87 (52), Fall Meet. Suppl., Abstract IN21A-1204, 2006.
- Thomas Doggett, R. Greeley, R. Castano, S. Chien, A. G. Davies, D. Tran, D. Mazzoni, V. Baker, J. Dohm, F. Ip. On-Board Cryosphere Change Detection With The Autonomous Sciencecraft Experiment. Eos Trans. AGU, 87 (52), Fall Meet. Suppl., Abstract IN53A-0817, 2006.
- Clare Averill, Dominic Mazzoni, Jennifer Logan, Lingling Tong, David Diner, and Qinbin Li. Combining MISR and MODIS Data to Automatically Catalog Smoke Plumes in North America. The Earth Observer, 17 (6), pp. 11-12, Nov-Dec 2005.
- Kiri L. Wagstaff, Henry P. Shu, Dominic Mazzoni, and Rebecca Castano. Semi-Supervised Data Summarization: Using Spectral Libraries to Improve Hyperspectral Clustering. The Interplanetary Network Progress Report, vol. 42-163, November 2005.
- Michael J. Garay, Dominic Mazzoni, Ákos Horváth, Roger Davies. The Synergistic Use of MISR and MODIS Observations from the Terra Satellite to Observe Thin Cirrus Clouds. Eos Trans. AGU, 86 (52), Fall Meet. Suppl., Abstract IN31A-1141, 2005.
- Dominic Mazzoni, Lingling Tong, David Diner, Qinbin Li, Jennifer Logan. Using MISR and MODIS Data For Detection and Analysis of Smoke Plume Injection Heights Over North America During Summer 2004. Eos Trans. AGU, 86 (52), Fall Meet. Suppl., Abstract A21B-0853, 2005.
- Brian D. Wilson, G. Manipon, B. Tang, D. Mazzoni, E. Fetzer, E. Dobinson, T. Yunck. GENESIS SciFlo: Scientific Knowledge Creating on the Grid Using a Semantically-Enabled Dataflow Execution Environment. Eos Trans. AGU, 86 (52), Fall Meet. Suppl., Abstract IN32A-07, 2005.
- Kiri Wagstaff and Dominic Mazzoni. Recent HARVIST Results: Classifying Crops from Remote Sensing Data. Proceedings of the Second NASA Data Mining Workshop, May 2006.
- Kiri L. Wagstaff, Dominic Mazzoni, and Stephan Sain. HARVIST: A System for Agricultural and Weather Studies Using Advanced Statistical Models. Proceedings of the Earth-Sun Systems Technology Conference, June 2005.
- Dave Diner, Clare Averill, Dominic Mazzoni, et al. New Satellite Observations of Upper Tropospheric/Lower Stratospheric Aerosols: Case Studies over the U.S. and Canada. Eos Trans. AGU, 85 (47), Fall Meet. Suppl., Abstract A21B-0744, 2004.
- Michael Garay, Dominic Mazzoni, et al. Making Sense of Large, Complex Datasets: Using MISR's Multiangle and Multispectral Information to Detect Clouds and Aerosols. Eos Trans. AGU, 85 (47), Fall Meet. Suppl., Abstract SF51A-06, 2004.
- Tracy Purdum, Ken Hurst, and Dominic Mazzoni. Tracing Geologic Formations in Hyperspectral Imagery using Support Vector Machines. Eos Trans. AGU, 85 (47), Fall Meet. Suppl., Abstract NG43A-0440, 2004.
- Dennis DeCoste and Dominic Mazzoni. Fast Query-Optimized Kernel Machine Classification. NASA Tech Briefs, October 2004, page 61.
- Dominic Mazzoni, Kiri Wagstaff, and Rebecca Castaño. Using Trained Pixel Classifiers to Select Images of Interest. Interplanetary Network Progress Report, Volume 42-158, Summer 2004.
- Michael Garay, Dominic Mazzoni, and Roger Davies. Multiangle Remote Sensing of Optically Thin Cirrus Clouds. Eos Trans. AGU, 85 (17), Jt. Assem. Suppl., Abstract GC51A-03, 2004.
- Michael Garay, Dominic Mazzoni, Roger Davies, Kiri Wagstaff, Amy Braverman, and Dennis DeCoste. A Hybrid Global MISR Cloud Mask Using Support Vector Machines and Active Learning. Eos Trans. AGU, 84 (46), Fall Meet. Suppl., Abstract H11F-0913, 2003.
- Matthew Fluet, Dominic Mazzoni, and Joel Miller. Modeling an Asteroid Collision with Antarctica. Outstanding solution to 1999 Mathematical Contest in Modeling. UMAP Journal, Fall 1999.
- Dominic Mazzoni and Jorge Aarao. Three-Player Nim and More: An
Exploration of How to Generalize Mathematical Games.
Undergraduate Senior Thesis, Harvey Mudd College, June 1999.