Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn how to streamline the deployment of AI models from development to production on edge devices through a practical, vendor-neutral workflow that eliminates trial-and-error approaches. This 59-minute conference talk addresses the significant challenges developers face when deploying models across diverse hardware platforms including phones, SoCs, and development boards, where each device introduces unique constraints that make performance unpredictable. Discover a systematic approach based on remote device execution and performance profiling that enables repeatable processes, facilitates fair hardware comparisons, and provides concrete on-device data to support informed design decisions. Explore how this methodology transforms the traditionally difficult and time-consuming process of edge AI deployment into a more efficient and predictable workflow, helping developers overcome the complexities of hardware-specific optimization and accelerate their time-to-device deployment cycles.
Syllabus
EDGE AI Talks: Faster Time-To-Device with Embedl Hub
Taught by
EDGE AI FOUNDATION