In this talk, we’ll show why Lattice’s low-power FPGA devices, coupled with the sensAI software stack, are a compelling solution for implementation of sophisticated AI capabilities in edge devices. The latest release of the senseAI stack provides a performance increase of more than 10X compared with the previous release. This performance increase is driven by updates to the CNN IP and the neural network compiler tool, including a number of new features, such as support for 8-bit activation quantization and smart merging of layers. For a seamless user experience, the new release expands the list of neural network topologies and machine learning frameworks supported, and automates the quantization and fraction settings processes. In addition, we provide a comprehensive set of reference designs which include training datasets and scripts for popular machine learning frameworks, enabling easy customization. And, to speed time to market for popular use cases, we provide full turnkey solutions for human counting, human presence detection and key phrase detection.
Accelerate Adoption of AI at the Edge with Easy to Use, Low-power Programmable Solutions
Session Speakers
-
Hussein Osman
Consumer Segment Manager, Lattice
Hussein Osman currently manages the consumer segment at Lattice Semiconductor. He is responsible for driving integration of Lattice products and solutions into consumer products such as mobile devices, wearables and IoT devices. In his roles at Lattice, Hussein managed the definition and execution of Lattice’s strategy to enter the AI applications space and he has contributed to the definition and launch of AI solutions using Lattice’s low-power FPGAs. Hussein has over 15 years of experience in the semiconductor industry. He has worked as a system engineer in touch sensing, capacitive sensing, fingerprint and USB technologies. He received his bachelor’s degree in Electrical Engineering from California Polytechnic State University, San Luis Obispo. He has spoken on AI topics at major conferences including the Embedded World Conference in 2018 and 2019.
