Using a well-known machine learning technique, soldiers quickly recognise threats like a vehicle-borne improvised explosive device, or potential danger zones from aerial war zone images

New York: A novel machine learning technique could help soldiers to learn 13 times faster than conventional methods as well as help save lives, say researchers, including one of Indian-origin.

Using a low-cost, lightweight hardware and implementing collaborative filtering -- a well-known machine learning technique -- the team found that soldiers are able to decipher hints of information faster and more quickly deploy solutions, such as recognising threats like a vehicle-borne improvised explosive device, or potential danger zones from aerial war zone images.

This technique could eventually become part of a suite of tools embedded on the next generation combat vehicle, offering cognitive services and devices for war fighters in distributed coalition environments, said Rajgopal Kannan, a researcher, from the US Army Research Laboratory.

This work is part of Army's larger focus on artificial intelligence and machine learning research initiatives pursued to help to gain a strategic advantage and ensure war fighter superiority with applications such as on-field adaptive processing and tactical computing, he said. 

The paper on this new research won the best-paper award at the 26th ACM/SIGDA International Symposium on Field Programmable Gate Arrays in Monterey, California in February.