Skip to main content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Machine Learning For Optical Communication Systems

Optical Communications

 

NIST will hold a workshop at the Boulder Colorado Laboratories to discuss the role of machine learning (ML) in optical communication systems. Optical communication systems are increasingly used closer to the network edge and are expected to find use in new applications that require more intelligent functionality. Optical networks are needed to address the high speeds and low latency of 5G wireless networks. The analog nature of optical transmission and the complexity of operation and management remain an impediment to greater use of software controls. Furthermore, optical systems are running up against spectral density limits that threaten traditional capacity-based scaling. New efficiency-based scaling methods are needed to further improve the cost/bit/s without relying on capacity improvements alone. Artificial intelligence (AI) and machine learning provide a new direction with the potential to both enable wider use of software controls and to further optimize the efficiency of optical systems across multiple dimensions. Reference data sets for ML would improve functionality and operability across industry further enabling scaling and efficiency.  This workshop seeks to identify and develop applications of AI, and ML in the context of accelerating the use of software-based networking in optical systems for improved performance and scalability. Paths to realizing reference training data sets for ML in optical communications systems including needs for new or different metrology will be examined. Workshop outcomes include a white paper for a plan and path to develop and disseminate reference data sets for ML training and applications to open and programmable optical communication systems, as well as a working group to further develop these ideas.

 

Please check back for further updates related to this workshop

 

Presentation Slides from August 2, 2019 Workshop on Machine Learning for Optical Communications Systems

Agenda (Printable PDF)

Workshop on Machine Learning For Optical Comm Systems
Friday, August 2nd, 2019
NIST Boulder, Colorado Campus


7:00 – 8:00 Continental Breakfast
8:00 – 8:30 Welcome and Opening Remarks
8:30 – 9:15 Keynote: “Machine Learning for Optical Communication Systems”

  • Speaker: Massimo Tornatore (Politecnico di Milano, Italy)

9:15 – 9:30 Coffee Break
9:30 – 11:30 Morning Talks (35 min each + 5 min questions)

  • Topic 1: “What data matters in optical communications”
    • Speaker: Dr. Uiara Celine (Technical University of Denmark)
  • Topic 2: “Machine learning models”
    • Speaker: Joao Pedro (Infinera)
  • Topic 3: “Data starved systems”
    • Speaker: Michael Majurski (NIST)

11:30-12 pm Morning Speaker Panel- Discussion to address questions from morning talks. (Panel Moderator: Dan Kilper)

12:00 – 13:00 Lunch (available for registered attendees only)
13:00 – 14:00 Afternoon speaker panel facilitated by 3 Flash Talks/ 5 min each.
(Panel Moderator: Abdella Battou)

  • Flash Talk 1: “Possible data sets coming from coherent transponders”
    • Speaker: Jim Westdorp (Ciena)
  • Flash Talk 2: “Data from ROADM / optical layer”
    • Speaker: Dan Kilper (University of Arizona)
  • Flash Talk 3: “Cross-layer/multi-vendor end-to-end networking”
    • Speaker: Jesse Simsarian (Nokia-Bell Labs)

14:00 – 15:00 Breakout groups lead by flash talk speakers
15:00 – 15:15 Coffee Break
15:15 – 16:00 Readout from breakout groups
16:00 – 16:30 Discussion on draft white paper
16:30 – 17:00 Next steps: working groups and follow up workshop

  • Signup sheet for working group.

A block of room have been arranged at the Best Western Plus Boulder Inn

online code:  https://www.bestwestern.com/en_US/book/hotel-rooms.06103.html?groupId=8H6DL4H6

•        Group code: call 800-233-8469 and reference code " NIST Machine Learning "

•        Arrival Date: Thursday, August 1, 2019

•        Departure Date: Saturday, August 3, 2019

•        Group Rates: $174 for a room with one king bed

Book by July 1, 2019 in order to guarantee the rate.

If you are not registered, you will not be allowed on site.  Registered attendees will receive security and campus instructions prior to the workshop.

NON U.S. CITIZENS PLEASE NOTE:  All foreign national visitors who do not have permanent resident status and who wish to register for the above meeting must supply additional information. Failure to provide this information prior to arrival will results, at a minimum, in significant delays in entering the facility. Authority to gather this information is derived from United States Department of Commerce Department Administrative Order (DAO) number 207-12.

* New Visitor Access Requirement: Effective July 21, 2014, under the REAL ID Act of 2005, agencies, including NIST, can only accept a state-issued driver’s license or identification card from states that are REAL ID compliant or have an extension.  See the Department of Homeland Security (DHS) site for the current compliance list.

NIST currently accepts other forms of federally issued identification in lieu of a state-issued driver’s license, such as a valid passport, passport card, DOD’s Common Access Card (CAC), Veterans ID, Federal Agency HSPD-12 IDs, Military Dependents ID, Transportation Workers Identification Credential (TWIC), and TSA Trusted Traveler ID.

Created May 3, 2019, Updated October 25, 2019