Best Practices: IITH Incubated startup VaccineonWheels Help in Covid-19 Vaccination in Telengana  |  Technology Inceptions: Battery Powered By Human Perspiration  |  Teacher Insights: Idea Sharing Improves MOOCS Learning  |  Parent Interventions: Confident Parent, Better Homeschooling  |  Life Inspirations: No Learning On an Empty Stomach  |  Leadership Instincts: Survival Skills in a Complex World  |  Technology Inceptions: LG Ultragear Gaming Speaker GP9  |  Teacher Insights: Focus, Gaming Mode in Zoom Meet  |  Management lessons: Work Ethics for a Post Pandemic World  |  Career News: 13 Japanese companies to attend JAPAN DAY 2021 @IIT Hyderabad  |  Higher Studies: IELTS Mock Tests: Benefits and Characteristics  |  Teacher Insights: New Features in Moodle 4.0  |  Policy Indications: India-US Launch Climate Action and Finance Mobilisation Dialogue  |  Science Innovations: Stanford University Develops Algorithm to Predict Molecular Structures  |  Technology Inceptions: Oxygen Concentrator, Generation System Developed by Indian Institute of Science  |  
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