[Semiconductor Engineering] How To Measure ML Model Accuracy

What’s good enough for one application may be insufficient for another. By Bryon Moyer 2021-04-01 Source: https://semiengineering.com/how-to-measure-ml-model-accuracy/ Perceive CEO Steve Teig spoke with Bryon Moyer of Semiconductor Engineering about the … Continued

[The Linley Group] A Guide to Processors for Deep Learning

By Linley Gwennap and Mike Demler Source: https://www.linleygroup.com/report_detail.php?num=76# Perceive has been included in the most recent version of a comprehensive report from The Linley Group, a leading supplier of independent analysis and consulting … Continued

[Topio Networks] Edge AI Landscape

2020-11-18 We are honoured to be included in Topio Networks’ Edge AI Landscape. Download the full landscape here.

[GlobeNewswire] The Best of Sensors 2020 Award Winners Unveiled During Questex’s Sensors Innovation Week Fall

Showcases the Year’s Best Innovations, Technologies, Teams and Individuals in the Sensors Industry By Questex LLC 2020-11-16 Source: https://www.globenewswire.com/news-release/2020/11/16/2127797/0/en/The-Best-of-Sensors-2020-Award-Winners-Unveiled-During-Questex-s-Sensors-Innovation-Week-Fall.html NEW YORK, Nov. 16, 2020 (GLOBE NEWSWIRE) — Today at an awards … Continued

[EETimes] AI and Vision at the Edge

By Jeff Bier 2020-09-06 Source: https://www.eetimes.com/dont-be-misled-by-accuracy-3-insights-for-more-useful-ai-models/ Things move fast. Not that long ago, AI and computer vision seemed like the stuff of science fiction — and now suddenly they’re everywhere, … Continued

[Security Systems News] Shifting from Sensors to Perceivers

Tiny chip helps ensure privacy by bringing and keeping data-center-class analytics at the edge By Ginger Hill 2020-08-26 Source: https://www.securitysystemsnews.com/article/shifting-from-sensors-to-perceivers YARMOUTH, Maine—Motivated to find a way to take cloud-level analytics, … Continued

[Fast Company] You can now buy an Amazon Echo add-on that stops Alexa from listening

Alexagate is the latest effort from MSCHF, a Brooklyn-based startup that makes limited-run products with a rhetorical flourish. In this case, MSCHF’s point of view is that Amazon is snooping on users through its Echo speakers, and that users should have an easier way to turn off the mics. Kevin Wiesner, MSCHF’s creative director, calls Alexagate an “aftermarket privacy adjustment” with an adversarial bent.

[Semiconductor Engineering] Week In Review: Design, Low Power

MaxLinear buys Intel’s Home Gateway biz; high-performance embedded IP; edge inference; sensor fusion. By Jesse Allen 2020-04-10 Source: https://semiengineering.com/week-in-review-design-low-power-89/ MaxLinear will acquire Intel’s Home Gateway Platform Division. MaxLinear, a provider of RF, analog, and … Continued

[insideBIGDATA] Latest News – 4/7/2020

In this regular column, we’ll bring you all the latest industry news centered around our main topics of focus: big data, data science, machine learning, AI, and deep learning.

[Stacey on IoT] Two startups find ways to bring AI to the edge

By Stacey Higginbotham 2020-04-06 Source: https://staceyoniot.com/two-startups-find-ways-to-bring-ai-to-the-edge/ The market for specialty silicon that enables companies to run artificial intelligence models on battery-sipping and relatively constrained devices is flush with funds and … Continued

[Forbes] Tenstorrent Launches AI Chip With Conditional Execution

By Karl Freund, Moor Insights and Strategy 2020-04-06 Source: https://www.forbes.com/sites/moorinsights/2020/04/07/tenstorrent-launches-ai-chip-with-conditional-execution/#34d1416a4bc7 What the heck is that you ask?  So, did I; but it looks promising! I continue to be amazed at … Continued

[EETimes] Startup Reinvents Neural Network Maths, Launches 20mW Edge AI Chip

A silicon valley startup claims it has reinvented the mathematics of neural networks and has produced a complementary edge AI chip, already sampling, which does not use the usual large array of multiply-accumulate units. The chip can run the equivalent of 4 TOPS, with impressive power consumption of 55 TOPS/W, and according to the company, achieves data-center class inference in under 20mW (YOLOv3 at 30fps).

[EE News Analog] Perceive launches edge AI inference processor

A 2018 startup and subsidiary of Xperi Corp. – Perceive Corp. (San Jose, Calif.) – has developed an edge machine learning chip called Ergo.

The chip requires custom software training but achieves 55 TOPS/W inferencing, 20x to 100x  higher than the efficiency of many alternatives. This begs the question what in the case of the Ergo chip is an operation?

[Forbes] Perceive Claims 20-100X AI Efficiency At The Edge

Perceive Corporation, a spinout from audio and image chip company Xperi, claims to have put data center class processing into a low cost, 20 milliwatt 7×7 mm chip, delivering 55 TOPS/Watt for edge device AI. Since 2-5 TOPS/Watt is now considered world-class for edge devices, I was initially skeptical. Upon further examination though, it looks like these guys may be on to something interesting here.

[Venture Beat] Perceive emerges from stealth with Ergo edge AI chip

By Kyle Wiggers 2020-03-31 Source: https://venturebeat.com/2020/03/31/perceive-emerges-from-stealth-with-ergo-edge-ai-chip/ On-device computing solutions startup Perceive emerged from stealth today with its first product: the Ergo edge processor for AI inference. CEO Steve Teig claims … Continued