Photo of the Week: LANL's On-Chip Neuromorphic Backpropagation Algorithm for Energy-Efficient Machine Learning

The Photo of the Week visually showcases the exciting work federal labs do every day! 

About this photo:

Los Alamos National Laboratory, a member of the Intel Neuromorphic Research Community, developed the open-source On-Chip Neuromorphic Backpropagation Algorithm (ONBA) to provide low-power machine learning (ML) on brain-like (neuromorphic) computers. This is the first implementation of the industry standard for ML on a neuromorphic computer. Scientists ran the algorithm on Intel’s Loihi chip, which emulates how the brain communicates via voltage spikes. Providing inference and learning entirely on-chip greatly reduced power usage compared with standard computer architecture. ONBA supports energy-efficient neuromorphic ML architectures to decrease the carbon footprint of ML and enable autonomous devices, such as drones, satellites and robots.

Photo credit: David Woodfin, Brenda Fleming and Allen Hopkins, LANL.

About the federal lab:

Los Alamos National Laboratory, a multidisciplinary research institution engaged in strategic science on behalf of national security, is managed by Triad, a public service oriented, national security science organization. Los Alamos enhances national security by ensuring the safety and reliability of the U.S. nuclear stockpile, developing technologies to reduce threats from weapons of mass destruction, and solving problems related to energy, environment, infrastructure, health, and global security concerns.