Business

August 31, 2018
 

Raytheon developing system that lets artificial intelligence explain itself

Under the Defense Research Project Agency’s Explainable Artificial Intelligence program, Raytheon BBN Technologies is developing a first of its kind neural network that explains itself.

The XAI program aims to create a suite of machine learning techniques that produce more explainable models while maintaining a high level of performance. It also aims to help human users understand, appropriately trust and effectively manage the emerging generation of artificially intelligent partners.

Raytheon BBN’s Explainable Question Answering System will allow AI programs to ‘show their work,’ increasing the human user’s confidence in the machine’s suggestions. “Our goal is to give the user enough information about how the machine’s answer was derived and show that the system considered relevant information so users feel comfortable acting on the system’s recommendation,” said Bill Ferguson, lead scientist and EQUAS principal investigator at Raytheon BBN.

EQUAS will show users which data mattered most in the AI decision-making process. Using a graphical interface, users can explore the system’s recommendations and see why it chose one answer over another. The technology is still in its early phases of development but could potentially be used for a wide-range of applications.

“A fully developed system like EQUAS could help with decision-making not only in DOD operations, but in a range of other applications like campus security, industrial operations and the medical field,” said Ferguson. “Say a doctor has an x-ray image of a lung and her AI system says that its cancer. She asks why and the system highlights what it thinks are suspicious shadows, which she had previously disregarded as artifacts of the X-ray process. Now the doctor can make the call — to diagnose, investigate further, or, if she still thinks the system is in error, to let it go.”

As the system is enhanced, EQUAS will be able to monitor itself and share factors that limit its ability to make reliable recommendations. This self-monitoring capability will help developers refine AI systems, allowing them to inject additional data or change how data is processed. 




All of this week's top headlines to your email every Friday.


 
 

 

Headlines – September 19, 2018

News North Korea’s Kim agree to inspections in bid to salvage nuclear talks – North Korea said on Sept. 19 it would permanently abolish its key missile facilities in the presence of foreign experts, the latest gesture by leader Kim Jong Un to revive faltering talks with Washington over his country’s nuclear program.    ...
 
 

News Briefs – September 19, 2018

Air Force: Space Force would cost $13 billion over 5 years Creating a Space Force as a separate military service, as proposed by President Donald Trump, would cost an estimated $12.9 billion in its first five years, according to a detailed Air Force plan for how to go about it. This is the first publicly...
 
 
Northrop Grumman photograph

Northrop Grumman showcases autonomous maritime capabilities

Northrop Grumman photograph Northrop Grumman’s Fire Scout autonomous surrogate launches a sonobuoy as part the 2018 Advanced Naval Training Exercise in Newport, Rhode Island. Northrop Grumman in collaboration with industry pa...