Artificial Intelligence

artificial intelligence (AI) design models machine learning

ARLINGTON, Va. – U.S. military researchers are asking industry to develop a new class of computer-generated design models with embedded machine-learning algorithms to help engineers develop and train artificial intelligence (AI) systems more quickly and accurately than they can today.

Officials of the U.S. Defense Advanced Research Projects Agency (DARPA) in Arlington, Va., issued a solicitation on Thursday (DARPA-PA-20-02-04) for the Ditto: Intelligent Auto-Generation and Composition of Surrogate Models project.

Modern machine learning algorithms have proven to be excellent mathematical stand-ins for real-world functions, yet suffer from two key drawbacks: lack of meta-cognition, and lack of composability, DARPA researchers explain.

Machine learning algorithms today store and incorporate new information solely by training on additional data; these models have no knowledge of what real-world functions or systems they represent. Furthermore, these machine learning models typically are trained and deployed in isolation.

Related: AI, machine learning driving embedded bus-and-board development

Instead, the Ditto program seeks to develop an automated software framework that can take in a microelectronics system design, train machine learning design models of subsystem components, and enable them to expand and collapse into appropriate levels of hierarchy.

This framework will enable engineers to make more informed decisions earlier in the design process, detect faults quickly, and mitigate risk for critical military applications.

Today’s system modeling technology can be slow, cumbersome, and not always accurate. The DARPA Ditto program seeks to develop an AI framework that can learn to generate surrogate models for different components of a complex system intelligently, aggregate these models while maintaining and communicating surrogate accuracy and coverage, and then integrate these models into one design.

Related: Air Force researchers ask industry for SWaP-constrained embedded computing for artificial intelligence (AI)

The program will focus on simulating integrated circuits (ICs), mixed-signal circuit boards, and networked-distributed systems. The framework should optimize iteratively so it can adapt continuously as it is exposed to more designs, and learn from past mistakes.

Ditto frameworks will address one of three different system design types to explore: integrated circuits (ICs), mixed-signal circuit boards, or networked distributed systems. Proposers should choose one of these three types.

The project first will develop a bare-bones framework that demonstrates functional capabilities by applying a wide variety of third-wave AI techniques to generate surrogate models automatically and enable rapid full-system simulation.

Related: IARPA seeks to apply trusted computing to artificial intelligence and machine learning models

Then the project will develop a proof-of-concept framework with meaningful performance gains in a full-system simulation. The entire Ditto project should be worth about $1 million.

Companies interested should submit proposals no later than 6 Nov. 2020 to the DARPA BAA website at Email questions or concerns to the Ditto program manager, Serge Leef, at

More information is online at


Leave a Reply