Mastodawn

Sebastian Büttrich @ ITU Apr 14

Always a favorite - FruitML = teaching simple #TinyML with #fruit detection as the task, in our #IoT course

#yolo #mobileNets #InternetOfThings #MachineLearning #EdgeImpulse #TeachableMachines

#thereIsNoAI
#thereIsInParticularNoSustainableAI

but some tiny ML is fun

#whoNeedsDataCenters

Show thread

Tim Riemann Mar 27

@rena2019 Hmm... ob der Goertzel allein da schon ausreicht!? Könnte mir vorstellen, dass man da doch eher "Sound Profile" benötigt und lieber mit TinyML sich ein Modell für den uC baut. #EdgeImpulse wäre dafür eigentlich genau das Richtige - weiss nur nicht, ob die auch die ESPs unterstützen.

cnx-software.com [Unofficial]Feb 23

OnLogic Factor 101 – A fanless industrial edge AI computer with Qualcomm QCS6490 SoC, 10GbE networking

https://fed.brid.gy/r/https://www.cnx-software.com/2026/02/23/onlogic-factor-101-a-fanless-industrial-edge-ai-computer-with-qualcomm-qcs6490-soc-10gbe-networking/

OnLogic Factor 101 – A fanless industrial edge AI computer with Qualcomm QCS6490 SoC, 10GbE networking

The OnLogic Factor 101 (FR101) is an ultra-small form factor, fanless industrial computer built around the Qualcomm QCS6490 platform for edge AI and data gateway applications. Designed for space-constrained applications, it targets light machine vision, inspection, monitoring, and low-speed autonomous systems. The octa-core Qualcomm Kryo 670 (Cortex-A78/A55-class) processor is paired with 8GB LPDDR4x memory and 128GB UFS flash storage. The fanless system features 10GbE and Gigabit Ethernet ports, five USB ports, and HDMI and USB-C (DisplayPort) video output. Its compliance with various standards makes it suitable for general office and industrial edge deployments. OnLogic Factor 101 specifications: SoC – Qualcomm Dragonwing QCS6490 CPU – Octa-core Kryo 670 with 1x Gold Plus core (Cortex-A78) @ 2.7 GHz, 3x Gold cores (Cortex-A78) @ 2.4 GHz, 4x Silver cores (Cortex-A55) @ up to 1.9 GHz GPU – Adreno 643L GPU @ 812 MHz with support for Open GL ES 3.2, Open CL 2.0, Vulkan

CNX Software - Embedded Systems News

Show thread

Gareth Halfacree Dec 1

And finally, for now, a look at a live Q&A session the #Arduino team did alongside representatives from #Qualcomm, #STMicro, and #EdgeImpulse - mostly about the new Arduino UNO Q and the App Lab, but naturally fielding a *lot* of questions about the new terms and conditions and whether Arduino's moving away from its open source ethos (again.)

https://www.hackster.io/news/arduino-hosts-q-a-on-the-arduino-uno-q-once-again-states-its-100-commitment-to-open-source-ethos-b99d96c3f08d

#News #Technology #Microcontroller #DevelopmentBoard #Embedded #Hackster

Arduino Hosts Q&A on the Arduino UNO Q, Once Again States Its "100% Commitment" to Open Source Ethos

Representatives from Arduino, Qualcomm, Edge Impulse, and STMicro answer the community's questions — and seek to allay fears.

Hackster.io

Alasdair Allan Jun 24, 2024

Another interesting example of mixture-of-agents architectures, this one from the folks at #EdgeImpulse combining #LLM and #TinyML at the edge. https://www.edgeimpulse.com/blog/using-llms-to-analyze-and-label-satellite-imagery-in-edge-impulse/

Using LLMs to Analyze and Label Satellite Imagery in Edge Impulse

With Edge Impulse's newest feature, visual data from a satellite can be labeled via GPT-4o both for cloud type and for coverage, generating two useful edge models from the same dataset very quickly.

Edge Impulse

Sebastian Büttrich @ ITU Apr 4, 2024

Back to earth, we re doing #FruitML today as part of #IoT course -

fruit classification on 256 kB of RAM, with #TinyML #EdgeImpulse #Arduino #NanoBLESense

Show thread

ishotjr ✨💙✨💗✨Jan 13, 2024

#EdgeImpulse, @hackaday, #Tindie, #DigiKey, #HackClub, and @seeedstudio! 🤘📛🤘

hannah Sep 27, 2023

Watching the Edge Impulse event - AI with hardware stuff makes vastly more sense as a value add than AI filling in for a Ouija board answering people's questions. Most people can't communicate with hardware very effectively, hardware has to actually just do the thing it's supposed to do without a person telling it what to do #EdgeImpulse #nvidia