Researchers Selected to Develop Novel Approaches to Lifelong Machine Learning
May 7, 2018 | DARPAEstimated reading time: 3 minutes

Machine learning (ML) and artificial intelligence (AI) systems have significantly advanced in recent years. However, they are currently limited to executing only those tasks they are specifically designed to perform and are unable to adapt when encountering situations outside their programming or training. DARPA’s Lifelong Learning Machines (L2M) program, drawing inspiration from biological systems, seeks to develop fundamentally new ML approaches that allow systems to adapt continually to new circumstances without forgetting previous learning.
Image caption: Today's machine learning and AI systems are limited to executing only tasks they are specifically programmed to perform, without being able to adapt to new situations outside of their training. DARPA's L2M program aims to generate new methodologies that will allow these systems to learn and improve during tasks, apply previous skills and knowledge to new situations, incorporate innate system limits, and enhance safety in automated assignments.
First announced in 2017, DARPA’s L2M program has selected the research teams who will work under its two technical areas. The first technical area focuses on the development of complete systems and their components, and the second will explore learning mechanisms in biological organisms with the goal of translating them into computational processes. Discoveries in both technical areas are expected to generate new methodologies that will allow AI systems to learn and improve during tasks, apply previous skills and knowledge to new situations, incorporate innate system limits, and enhance safety in automated assignments.
The L2M research teams are now focusing their diverse expertise on understanding how a computational system can adapt to new circumstances in real time and without losing its previous knowledge. One group, the team at University of California, Irvine plans to study the dual memory architecture of the hippocampus and cortex. The team seeks to create an ML system capable of predicting potential outcomes by comparing inputs to existing memories, which should allow the system to become more adaptable while retaining previous learnings. The Tufts University team is examining a regeneration mechanism observed in animals like salamanders to create flexible robots that are capable of altering their structure and function on the fly to adapt to changes in their environment. Adapting methods from biological memory reconsolidation, a team from University of Wyoming will work on developing a computational system that uses context to identify appropriate modular memories that can be reassembled with new sensory input to rapidly form behaviors to suit novel circumstances.
“With the L2M program, we are not looking for incremental improvements in state-of-the-art AI and neural networks, but rather paradigm-changing approaches to machine learning that will enable systems to continuously improve based on experience,” said Dr. Hava Siegelmann, the program manager leading L2M. “Teams selected to take on this novel research are comprised of a cross-section of some of the world’s top researchers in a variety of scientific disciplines, and their approaches are equally diverse.”
While still in its early stages, the L2M program has already seen results from a team led by Dr. Hod Lipson at Columbia University’s Engineering School. Dr. Lipson and his team recently identified and solved challenges associated with building and training a self-reproducing neural network, publishing their findings in Arvix Sanity. While neural networks are trainable to produce almost any kind of pattern, training a network to reproduce its own structure is paradoxically difficult. As the network learns, it changes, and therefore the goal continuously shifts. The continued efforts of the team will focus on developing a system that can adapt and improve by using knowledge of its own structure. “The research team’s work with self-replicating neural networks is just one of many possible approaches that will lead to breakthroughs in lifelong learning,” said Siegelmann.
“We are on the threshold of a major jump in AI technology,” stated Siegelmann. “The L2M program will require significantly more ingenuity and effort than incremental changes to current systems. L2M seeks to enable AI systems to learn from experience and become smarter, safer, and more reliable than existing AI.”
Testimonial
"The I-Connect007 team is outstanding—kind, responsive, and a true marketing partner. Their design team created fresh, eye-catching ads, and their editorial support polished our content to let our brand shine. Thank you all! "
Sweeney Ng - CEE PCBSuggested Items
Smart Automation: Odd-form Assembly—Dedicated Insertion Equipment Matters
09/09/2025 | Josh Casper -- Column: Smart AutomationLarge, irregular, or mechanically unique parts, often referred to as odd-form components, have never truly disappeared from electronics manufacturing. While many in the industry have been pursuing miniaturization, faster placement speeds, and higher-density PCBs, certain market sectors are moving in the opposite direction.
Machvision Leads Shift to Automated Inline Final Inspection, AOI in North America
09/10/2025 | Ralph Jacobo, all4-PCBSchweitzer Engineering Laboratories (SEL) chose Machvision inspection equipment due to its capabilities and versatility. Machvision of Taiwan offers circuit inspection, hole inspection and measurement, IC Substrate and HDI inspection, and final visual inspection solutions. The best fit for SEL was the 4.0Pro Circuit Inspection for inner and outer layers, and the AFI6 for final visual inspection of finished panels.
Closing the Loop on PCB Etching Waste
09/09/2025 | Shawn Stone, IECAs the PCB industry continues its push toward greener, more cost-efficient operations, Sigma Engineering’s Mecer System offers a comprehensive solution to two of the industry’s most persistent pain points: etchant consumption and rinse water waste. Designed as a modular, fully automated platform, the Mecer System regenerates spent copper etchants—both alkaline and acidic—and simultaneously recycles rinse water, transforming a traditionally linear chemical process into a closed-loop system.
U.S. Army Begins Fielding BAE Systems’ Mission-critical Software-defined Radios Across Rotary-wing Aviation Fleet
09/08/2025 | BAE SystemsBAE Systems’ AN/ARC-231A Multi-mode Aviation Radio Set (MARS) has completed initial installation and is operationally ready for use today on select U.S. Army rotary-wing aircraft.
AV Delivers First Two Multi-Purpose High Energy Laser Systems to U.S. Army
09/04/2025 | BUSINESS WIREAeroVironment, Inc. (AV) announced the successful delivery of the first two mobile counter-unmanned aircraft system (C-UAS) prototype Laser Weapon System (LWS) to the U.S. Army Rapid Capabilities and Critical Technologies Office (RCCTO) as part of the first increment of the Army Multi-Purpose High Energy Laser (AMP-HEL) prototyping effort.