to present and participate in discussions on the applications of machine learning to relevant problems
and datasets. While there are other venues to present
this type of work, NAML’s audience is unique due to
the large attendance by US Navy and DOD
researchers in contrast to the mostly academic or
industry attendees of other workshops. The third and
possibly most important impact of NAML is the
establishment of a grassroots-driven community of
interest around the topics of machine learning, computer vision, and artificial intelligence. It is our intention to continue holding the NAML workshop annually at SSC Pacific, although with a few potential
changes and additions. First, due to the popularity
and limited space for the event, we will steer the
workshop towards specific technology and problem
areas for the US Navy and accept abstracts in those
areas instead of opening the workshop to any application of machine learning. For instance, there was a
lot of interest in the use of machine learning on
cyber problems, so we will plan to hold a session
focused on that area. Second, we plan to hold smaller, more focused workshops whose goal is to tackle,
or at least make progress on, a specific problem within the US Navy. We hope to have researchers from
other US Navy labs and organizations lead these
workshops and report back their findings to the larger NAML audience each year. The third annual NAML
workshop is scheduled for 11–14 February at SSC
Pacific. More information about the workshop is
available at the workshop website.
SSC Pacific organized and ran the second annual
workshop on Naval Applications of Machine Learn-
ing (NAML) on February 13–15, 2018. The event was
well attended and was largely considered a great suc-
cess. This paper is an attempt to summarize the
event, impact, and future plans. The event spurred
many new, and fostered many continuing, collabo-
rations. We plan to continue organizing the work-
shop annually and to continue holding it at SSC
Pacific every winter, with the addition of specialized
and more focused workshops to be held between the
annual events. Events such as this are crucial to the
communication of ideas, problems, and solutions
between researchers in labs around the US Navy and
DOD and other organizations.
Agarwal, D.; Bersin, J.; Lahiri, G.; Schwartz, J.; and Volini, E.
2018. AI, Robotics, and Automation: Put Humans in the
Loop. Deloitte Insights, March 28. www2.deloitte.com/
Freedberg, S. J. Jr. 2018. Joint Artificial Intelligence Center
Created Under DoD CIO. Breaking Defense. June 29. break-
Gebhardt, D.; Parikh, K.; Dzieciuch, I.; Walton, M.; and
Hoang, N. A. V. 2017. Hunting for Naval Mines with Deep
Neural Networks. In OCEANS 2017–Anchorage, 1–5. Piscat-away, NJ: Institute for Electrical and Electronics Engineers.
Harguess, J.; Barngrover, C.; and Rahimi, A. 2017. An Analysis of Optical Flow on Real and Simulated Data with Degradations. In Proceedings of the International Society for Optics
and Photonics 10199: Geospatial Informatics, Fusion, and
Motion Video Analytics VII, 1019905. Bellingham, WA:
Harguess, J.; Marez, D.; and Ronquillo, N. 2018. An Investigation into Strategies to Improve Optical Flow on Degraded
Data. In Proceedings of the International Society for Optics and
Photonics 10645: Geospatial Informatics, Motion Imagery,
and Network Analytics VIII, 106450F. Bellingham, WA:
Kaiser, S. A.; Christianson, A. J.; and Narayanan, R. M. 2016.
Multistatic Radar Exploitation of Forward Scattering Nulls.
In Proceedings of the 2016 IEEE Radar Conference, 1–6. Piscat-away, NJ: Institute for Electrical and Electronics Engineers.
Lam, D.; Kuzma, R.; McGee, K.; Dooley, S.; Laielli, M.; Klar-ic, M.; Bulatov, Y.; and McCord, B. 2018. xview: Objects in
Context in Overhead Imagery. arXiv preprint. arX-
iv:1802.07856 [ cs.CV]. Ithaca, NY: Cornell University
Lee, D.; Siu, V.; Cruz, R.; and Yetman, C. 2016. Convolutional Neural Net and Bearing Fault Analysis. In Proceedings
of the International Conference on Data Mining, 194–200.
Athens, GA: CSREA Press.
Martin, K. M.; Wood, W. T.; and Becker, J. J. 2015. A Global
Prediction of Seafloor Sediment Porosity Using Machine
Learning. Geophysical Research Letters,
42( 24). doi.org/
Katie Rainey is a scientist at Space and Naval Warfare Systems Center Pacific, a U.S. Navy research laboratory in San
Diego, California. Her research interests include object
recognition in the maritime domain and AI robustness. She
also works to direct research to support defense applications, and is active in building the community of AI
researchers among defense laboratories. She has a PhD in
mathematics from the University of California, Irvine.
Josh Harguess has been with Space and Naval Warfare Systems Center Pacific for six years focusing on research in
computer vision and machine learning applied to applications of interest to the Navy and DoD, such as ship detection and tracking, video content analysis, 3D model generation, and Augmented Reality. He is an active researcher in
these areas with more than 45 publications and 5 patents.
He received his PhD from the University of Texas at Austin
working on face recognition from multiple video cameras.