Embedded ML: The New Secret Weapon to IoT Success

Login

About Arun Rajasekaran

Arun is a seasoned, cross-functional engineering leader, an innovator, and a thought leader in all aspects of embedded systems: from silicon to software. Arun currently leads Market development and Business development efforts for Edge Impulse – a ground-breaking embedded machine learning development and deployment platform. Previously, as CTO of Voice BU at Poly, Arun led Technology Strategy and Technology Platforming efforts with a focus on wearable technologies. Before becoming the CTO, while his primary focus was around leading Plantronics' product development teams responsible for IoT-to-Cloud system architecture, embedded software, audio DSP, AI/ML technologies, and data insights & analytics, he was also leading Plantronics's strategic collaboration and partnership efforts with silicon, SaaS, and other ecosystem partners. Prior to Poly, Arun has held various engineering leadership positions at BlackBerry/RIMM, Ikanos/Conexant/GlobeSpan, and 3Com/USRobotics.

About Edge Impulse

Edge Impulse is the leading development platform for machine learning on edge devices, free for developers and trusted by enterprises.

Home >

Embedded ML: The New Secret Weapon to IoT Success

Arun Rajasekaran - Edge Impulse- Watch Now - Duration: 41:54

Embedded ML: The New Secret Weapon to IoT Success

Arun Rajasekaran

Description Questions & Comments (4)

Attempting to add-on AI and ML modeling to existing IoT networks delivers marginal results compared to when it's designed into the architecture. Organizations that have accomplished this in their IIoT/IoT architectures can support model processing in multiple stages of their solution while reducing networking throughput and latency, making everything more purposeful and even more secure.

M↓ MARKDOWN HELP

italics	surround text with asterisks
bold	surround text with two asterisks
hyperlink	[hyperlink](https://example.com) or just a bare URL
code	surround text with `backticks`
~~strikethrough~~	surround text with ~~two tilde characters~~
quote	prefix with >

Upvotes Newest Oldest

davek

Score: 0 | 3 years ago | no reply

I like how you illustrated the difference between legacy IoT and embedded ML.

harrison_donahue

Score: 0 | 3 years ago | no reply

SO GOOD! As we try to pinch more and more value out of the data collected by our embedded systems, the complexity drives a need to change the way we approach the problem of analyzing and taking action on this data to cut down latency and cost. Great talk, Arun.

FelixBors

Score: 0 | 3 years ago | no reply

great overview of ML in small devices, and the future of the field; thank you

daveyboy17

Score: 0 | 3 years ago | no reply

Great overview of the eML landscape, Thanks