Teacher Insights: Access to SWAYAM and other digital initiatives goes up  |  Policy Indications: Major relief measures for power sector  |  Education Information: Kerala Government postpones KEAM Entrance Exam 2020  |  Policy Indications: COVID-19: UNICEF continues to ship vital supplies to affected countries   |  International Edu News: WHO Director-General calls on G20 to Fight, Unite, and Ignite against COVID-19  |  Education Information: WHO WhatsApp health alert launches in Arabic, French and Spanish  |  National Edu News: SJVN provides Rs 1 Cr for buying ventilators  |  Science Innovations: DST launches nationwide exercise to map & boost Covid19 solutions   |  National Edu News: Officers and staff of MNRE working from Home through e-office platform  |  National Edu News: Doordarshan to bring back famed Ramayan on Doordarshan National  |  Best Practices: Post Offices provide basic postal and financial services during COVID-19 lockdown  |  Leadership Instincts: Covid-19: Minister directs Kendriya Vidyalaya Sangathan to provide buildings   |  Education Information: National Testing Agency Postpones NEET UG May-2020  |  Leadership Instincts: Fight Corona IDEAthon   |  International Edu News: UK PM Boris Johnson tests positive for coronavirus  |  
February 19, 2020 Wednesday 11:56:32 AM IST

A new algorithm for efficient distributed deep learning by US army researchers

Teacher Insights

The U.S. Army Combat Capabilities Development Command's Army Research Laboratory researchers developed algorithms that facilitate distributed, decentralized and collaborative learning capabilities among devices, avoiding the need to pool all data at a central server for learning. "There has been an exponential growth in the amount of data collected and stored locally on individual smart devices," said Dr. Jemin George, an Army scientist at the U.S. Army Combat Capabilities Development Command's Army Research Laboratory. "Numerous research efforts, as well as businesses, have focused on applying machine learning to extract value from such massive data to provide data-driven insights, decisions, and predictions."

However, none of these efforts address any of the issues associated with applying machine learning to a contested, congested and constrained battlespace, George said. These battlespace constraints become more apparent when the devices are using deep learning algorithms for decision-making due to the heavy computational costs in terms of learning time and processing power.

"This research tries to address some of the challenges of applying machine learning, or deep learning, in military environments," said Dr. Prudhvi Gurram, a scientist who contributed to this research. 

Earlier, they developed a new technique to significantly decrease the communication overhead, by up to 70% in certain scenarios, without sacrificing the learning rate or performance accuracy. The researchers developed a triggering mechanism, which allowed the individual agents to communicate their model with their neighbors only if it has significantly changed since it was last transmitted. Army researchers are investigating how this research can be applied to the Internet of Battlefield Things, incorporating quantized and compressed communication schemes to the current algorithm to further reduce the communication overhead.


(Content Courtesy: https://www.eurekalert.org/pub_releases/2020-02/uarl-ard021820.php)

Comments