Questions and Answers:
- What is DARPA's ML2P Program? The aim is to create energy-efficient machine learning technologies that can operate in resource-constrained battlefield environments.
- Why is energy efficiency important for battlefield machine learning? Today's machine learning technology consumes a lot of electricity. This can overwhelm the limited power available from the batteries and generators in the battle zone.
- When and where would you briefly explain DARPA for ML2P? Available online for registered participants on Tuesday, August 26th, 2025 from 9am to 3pm at the DARPA Executive Conference Center in Arlington, VA.
Arlington, Virginia – Next week, US military researchers will briefly explain the industry with a new programme to develop energy-efficient machine learning capabilities for use in harsh environments on the battlefield.
Officials from the U.S. Defense Advanced Research Projects Agency (DARPA) in Arlington, Virginia will briefly describe the industry directly and online in a Mapping Machine Learning (ML2P) program, from 9am to 3pm on Tuesday, August 26, 2025.
ML2P aims to develop an innovative and sustainable approach to machine learning on power-hungry battlefields that do not have limited electricity on the battlefield, which usually comes from batteries and generators.
In-person briefings will be at DARPA Executive Conference Center, Wilson Blvd. 4075 in Arlington, VA, where you will receive your online virtual briefing logon credentials upon registration.
Amazing electricity demand
Machine learning technology uses enormous amounts of electricity today, which could overwhelm current generation and storage capabilities on the battlefield. The ML2P program aims to create energy-efficient machine learning technologies for the limited resources of the battlefield.
The ML2P program aims to develop innovative and sustainable approaches to machine learning to maintain innovation without compromising energy resources.
Machine learning at the edge works on resources constrained battlefields that require electrical efficiency. This solution could include machine learning that receives energy from a new generation.
DARPA researchers hope to borrow a technical approach to energy use from air, land, sea, and sea-based non-white crowding vehicles with limited battery capacity that must meet mission needs such as propulsion, communications, data processing, and mission planning.
Tell us more about the need for machine learning on the battlefield…
- Promoting the need for machine learning on the battlefield is an increase in the complexity, speed and data-driven nature of modern warfare. Machine learning on the battlefield helps you make quick decisions. Reduces data overload. Enhanced target recognition and tracking. Machine autonomy; Cybersecurity and electronic warfare (EW); Predictive maintenance and logistics. Psychological and Information Warfare. Machine learning, especially deep learning on a large scale – burns a lot of electricity because it quickly makes amazing maths with thousands or millions of parameters and training examples.
The ML2P program aims to enable accurate prediction of the power and performance of future machine learning models that understand power consumption throughout the machine learning lifecycle. This will encourage the development of more energy-efficient military computing, researchers say. ML2P provides a trade-off between energy and performance to build energy-aware machine learning that enables energy-aware machine learning.
Anyone interested in participating in face-to-face and online virtual ML2P briefings will be available to https://creative.spa.com/darpa/i2o/ml2p/pd/ on Monday, August 25th, 2025 by 5pm? You must register with p = registration. Registration is free.
Email DARPA with questions and concerns [email protected]. For more information, see https://sam.gov/oppp/aaba444f0eb8450a8ad430a28c595d36/view (
