Enable AI on Endpoint Devices - Without Writing Code
Intelligent IoT devices require sensor data collection, analysis, and AI to determine actionable insights. Most applications today send endpoint sensor data to the cloud for processing, which puts stress on the system's network and power requirements, adds latency, and reduces security. Implementing AI directly at the endpoint devices solves these challenges but has been impractical for most applications due to a lack of quality development tools focused on significant resource constraints of endpoint computing devices.
A complete endpoint AI development tool should consider data analytics, model building, and hardware implementation to deliver a low-power, optimized, and scalable solution. In this webinar, we will demonstrate how SensiML's software addresses each of these factors and eliminates the need for a large team of data scientists or firmware.Attendees will learn how to:
- Build intelligent endpoints quickly and easily from start to finish, optimized for low power at multiple levels and with significant time-to-market gains
- Generate the necessary algorithms and code for running on the endpoint device
- Get the most from endpoint AI: hardware-agnostic algorithm construction, edge learning and customization, and leveraging your installed user base for rapid crowdsourcing of algorithm improvements
Chris Rogers, CEO, SensiML Corporation
With over 25 years of experience running embedded systems, wireless communications, and algorithm development businesses, Chris has led high caliber teams at companies ranging from Intel to startups. Chris focuses on building and supporting teams capable of bringing cutting edge technologies to reality, delivering results, and customer value quickly. Prior to spinning out SensiML from Intel, Chris was general manager of Intel's Quark/Curie machine learning software tools business and held prior positions as product line manager turning around Intel's $750M business in Wi-Fi and Bluetooth modules. An engineer at heart, Chris started his career in automotive test/measurement as both developer and end-user of IoT systems well before the term came into vogue, building bespoke embedded systems for Michelin Tire and then as a consultant to test vendors for GM and Ford. He holds a bachelor's in Mechanical Engineering and an MBA from Carnegie Mellon's Tepper School of Business.