Defense Advanced Research Projects AgencyTagged Content List


Showing 30 results for Adaptability RSS
Today’s machine learning systems are restricted by their inability to continuously learn or adapt as they encounter new situations; their programs are fixed after training, leaving them unable to react to new, unforeseen circumstances once they are fielded. Adding new information to cover programming deficits overwrites the existing training set. With current technology, this requires taking the system offline and retraining it on a dataset that incorporates the new information. It is a long and arduous process that DARPA’s Lifelong Learning Machines (L2M) program is working to overcome.
Today’s electromagnetic (EM) spectrum is a scarce resource that is becoming increasingly congested and contested as friendly, unfriendly, and neutral entities vie for available spectrum resources at any given time, location, and frequency. Within the Department of Defense (DoD), radio frequency (RF) systems, such as communications networks and radar, must operate within this congested environment and contend with mission-compromising interference from both self- and externally generated signals. A desire to support wideband EM spectrum operations also adds to the burden, as current approaches to mitigating wideband receiver interference are sub-optimal and force compromises around signal sensitivity, bandwidth usage, and system performance.
March 14, 2019, 9:00 AM ET,
DARPA Conference Center
The Information Innovation Office is holding a Proposers Day meeting to provide information to potential proposers on the objectives of the new Artificial Social Intelligence for Successful Teams (ASIST) program. ASIST will explore human-machine teaming and machine social intelligence in a teaming context. DARPA envisions computer-based agents that observe their surroundings; build and maintain rich representations of the environment, team, and individuals; infer teammates’ goals (non-verbal behavior); predict teammates’ actions; and assist teams by planning interventions and executing them at appropriate times. During demonstrations in a virtual testbed, ASIST agents will operate in increasingly complex environments and will have to adapt to challenges such as a change in strategy.
February 20, 2019,
The Defense Advanced Research Projects Agency (DARPA) Defense Sciences Office (DSO) is sponsoring a Proposers Day webcast to provide information to potential proposers on the objectives of an anticipated Broad Agency Announcement (BAA) for the Competency-Aware Machine Learning (CAML) program. The Proposers Day will be held via prerecorded webcast on February 20, 2019 at 11:00 AM EST and will repost at 3:00 PM EST. Advance registration is required for viewing the webcast.
March 30, 2017,
DARPA Conference Center
In support of the Lifelong Learning Machines (L2M) program, DARPA will host a Proposers Day on March 30, 2017, at the DARPA Conference Center in Arlington, VA. The registration deadline for the event is March 24, 2017, at noon (EDT).