Machine Learning Inference In Under 5 mW with a Binarized Neural Network on an FPGA

Tuesday, May 22, 1:30 PM - 2:00 PM
Summit Track: 
Enabling Technologies
Exhibit Hall A-2

The demand for always-on intelligence is rapidly increasing in various applications. You can find cameras that are always watching for anomalies in a manufacturing line, monitoring vehicle speeds on roads, or looking for a specific gesture or person. Since these cameras have to be always on, security and power consumption becomes a concern. Users don’t want the captured images to be sent to the cloud (available for hackers to access) and therefore item or anomaly detection must occur locally vs. in the cloud. This increases local computational requirements, which potentially increases power consumption – a major issue for battery-powered products.

This presentation will provide an overview of how FPGAs, such as Lattice’s iCE40 UltraPlus, are able to implement multiple binarized neural networks in a single 2 mm x 2 mm package to provide always-on intelligence without relying on cloud computation.


Abdullah Raouf

Senior Marketing Manager, Lattice

Abdullah Raouf is a senior marketing manager for Lattice Semiconductor focused on demand creation for FPGA and ASSP solutions within the mobile market. In this role, he has worked with both internal & external development teams to create complete solutions as well as various demonstrations to globally showcase the technical capabilities and technical value propositions. He has more than 15 years of experience in semiconductor product management and holds a Bachelor of Science degree in Electrical Engineering from UC Davis and an MBA from Santa Clara University.

See you at the Summit! May 20-23 in Santa Clara, California!
Register today and reserve your hotel room!