The AI Whisperer
April 3, 2018 | Raytheon CompanyEstimated reading time: 2 minutes
A toddler with a Sharpie and a blank wall is a parents’ nightmare. It's hard to prevent bad choices when the child can't explain the reasoning behind them.
Aritificial intelligence presents a similar challenge. Where much of today's aritificial intelligence simply takes in information and pushes out data, users of software that manages massive amounts of data need to understand exactly how the systems approach a decision.
To trust increasingly sophisticated AI systems and make them more dependable, the government, industry and academia are studying how such machines make decisions. Raytheon is funding an internal research project that might provide some answers.
“People are hesitant to depend on AI for critical decision-making because there’s no way it can explain the why,’” said Raytheon engineering fellow Gabriel Comi. “My team’s research is providing a first step toward a trusted solution.”
Comi is working on a concept called “explainable artificial intelligence,” using software he calls "the AI whisperer." The code is written to interrogate another computer program systematically and thoroughly. Using responses from the subject software, the AI whisperer maps the information provided that's most relevant to producing the output. Like a researcher, a large part of Comi’s job is trying multiple configurations to see which ones work best.
Comi's research is designed to ensure human operators get the most out of aritifical intelligence technology.
“The goal is to allow people to work more efficiently and faster than our adversary. It is not about abdicating our authority,” said Comi. “As information becomes the dominant currency in conflict and the quantity of data grows exponentially, we need tools like this to close the gap. To do that, we need to rely on and trust artificial intelligence and machine learning.”
Instead of certainty and cause, AI works off probability and correlation, according to Comi. Studying their decision-making processes helps to make machines accountable for the things they learn, in ways that we can understand.
“As AI continues to advance, we need to be able to explain our answers to demonstrate that we arrived at those answers correctly,” said Comi. “That is something we all experienced in grade school when our teachers told us to show our work.”
Current technology cannot “show its work like in math class,” said Comi, because there is no way to ask the program to explain why it produced the answer it did. That's what his work is changing.
If Comi’s prototype is successful, it could go a long way toward developing trust in man-machine systems, something the U.S. Department of Defense, among others, wants to explore.
Man-machine teaming will help DoD forces keep up with the ever-changing landscape of threats.
“What is coming is amazing,” Comi said.
Suggested Items
Technica Leads the Way Into Automation and Machine Learning at IPC APEX EXPO 2024
03/28/2024 | Marcy LaRont, PCB007 MagazineAs a significant partner to PCB fabricators since almost the beginning of multilayer boards, Technica USA brings a lot of expertise to the industry. This year’s IPC APEX EXPO show will showcase their biggest booth yet, and a whole lot of information, discussion and demonstration around automation and AI machine learning. In this interview, Jason Perry discusses Technica's plans for the show, and why attendees should stop by.
Airbus to Acquire INFODAS and Strengthen its Cybersecurity Portfolio
03/25/2024 | AirbusAirbus Defence and Space has entered into an agreement to acquire INFODAS, a Cologne-based, German company that provides cybersecurity and IT solutions in the public sector including for defence and critical infrastructures.
ROCKA Solutions Unveils New Website Design to Enhance Customer Experience
02/12/2024 | ROCKA SolutionsROCKA Solutions is excited to announce the launch of its redesigned website. The new website features a modern design aimed at improving the overall user experience and streamlining the inquiry and order process for customers.
SAIC Awarded $375 Million U.S. Navy Contract for Modern Vehicle Fielding Integration and Support
01/10/2024 | SAICThe U.S. Navy has awarded Science Applications International Corp. a $375 million contract to continue providing Command, Control, Communications, Computers (C4) Intelligence, Surveillance and Reconnaissance (ISR) fielding and integration on land-based vehicle platforms to support Naval Information Warfare Center Atlantic (NIWC Atlantic).
Quantum Computer Sources Majority of Components from Japanese Makers
12/20/2023 | ACN NewswireThe newly developed superconducting quantum computer uses a 64 qubit chip provided by RIKEN, which leverages the same design as the chip in RIKEN's first superconducting quantum computer, which was unveiled to users in Japan as a cloud service for non-commercial use on March 27, 2023.