med-mastodon.com is one of the many independent Mastodon servers you can use to participate in the fediverse.
Medical community on Mastodon

Administered by:

Server stats:

344
active users

#TinyML

0 posts0 participants0 posts today
Alasdair Allan<p>Shooting video ahead of my talk at <a href="https://mastodon.social/tags/ParticleSpectra" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ParticleSpectra</span></a> in a couple of weeks time. <a href="https://mastodon.social/tags/IoT" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>IoT</span></a> <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://spectra.particle.io/?utm_campaign=spectra_2024&amp;utm_content=webinar&amp;utm_source=x&amp;utm_medium=social" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">spectra.particle.io/?utm_campa</span><span class="invisible">ign=spectra_2024&amp;utm_content=webinar&amp;utm_source=x&amp;utm_medium=social</span></a></p>
Alasdair Allan<p>Huh! Just stumbled across the Analog Devices MAX78000. It's a Cortex M4F with an on-chip CNN accelerator. This looks rather interesting, <a href="https://github.com/analogdevicesinc/MaximAI_Documentation" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/analogdevicesinc/Ma</span><span class="invisible">ximAI_Documentation</span></a>. Anyone had a play? How's the development toolchain? <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a></p>
Alasdair Allan<p>Another interesting example of mixture-of-agents architectures, this one from the folks at <a href="https://mastodon.social/tags/EdgeImpulse" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>EdgeImpulse</span></a> combining <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> and <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> at the edge. <a href="https://www.edgeimpulse.com/blog/using-llms-to-analyze-and-label-satellite-imagery-in-edge-impulse/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">edgeimpulse.com/blog/using-llm</span><span class="invisible">s-to-analyze-and-label-satellite-imagery-in-edge-impulse/</span></a></p>
Alasdair Allan<p>By me for <span class="h-card" translate="no"><a href="https://noc.social/@hackster_io" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>hackster_io</span></a></span>, "The CH32, just another 10¢ microcontroller?" The latest project to appear for the 10¢ CH32 RISC-V microcontroller is a tiny wake word engine with impressive accuracy levels. <a href="https://mastodon.social/tags/tinyml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tinyml</span></a> <a href="https://www.hackster.io/news/the-ch32-just-another-10-microcontroller-a4e5f894ba76" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">hackster.io/news/the-ch32-just</span><span class="invisible">-another-10-microcontroller-a4e5f894ba76</span></a></p>
Alasdair Allan<p>By me for <span class="h-card" translate="no"><a href="https://noc.social/@hackster_io" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>hackster_io</span></a></span>, "Benchmarking TensorFlow and TensorFlow Lite on Raspberry Pi 5." The big take away from these new benchmarks is that the Raspberry Pi 5 has similar performance when using TensorFlow Lite to the Coral TPU, displaying essentially the same inferencing speed as Google's accelerator hardware. <a href="https://mastodon.social/tags/ML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ML</span></a> <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/TensorFlow" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TensorFlow</span></a> <a href="https://mastodon.social/tags/RaspberryPi" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RaspberryPi</span></a> <a href="https://mastodon.social/tags/CoralTPU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CoralTPU</span></a> <a href="https://www.hackster.io/news/benchmarking-tensorflow-and-tensorflow-lite-on-raspberry-pi-5-b9156d58a6a2" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">hackster.io/news/benchmarking-</span><span class="invisible">tensorflow-and-tensorflow-lite-on-raspberry-pi-5-b9156d58a6a2</span></a></p>
Alasdair Allan<p>By me for <span class="h-card" translate="no"><a href="https://noc.social/@hackster_io" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>hackster_io</span></a></span>, "Bringing GPT-4o in From the Cloud to the Edge." <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> <a href="https://mastodon.social/tags/SmallAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SmallAI</span></a> <a href="https://www.hackster.io/news/bringing-gpt-4o-in-from-the-cloud-to-the-edge-289fbf6e0978" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">hackster.io/news/bringing-gpt-</span><span class="invisible">4o-in-from-the-cloud-to-the-edge-289fbf6e0978</span></a></p>
Alasdair Allan<p>By me for <span class="h-card" translate="no"><a href="https://noc.social/@hackster_io" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>hackster_io</span></a></span>, "Creating cross-platform Small AI with PicoLLM." <a href="https://www.hackster.io/news/creating-cross-platform-small-ai-with-picollm-3cf6076db9ec" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">hackster.io/news/creating-cros</span><span class="invisible">s-platform-small-ai-with-picollm-3cf6076db9ec</span></a> <a href="https://mastodon.social/tags/tinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tinyML</span></a> <a href="https://mastodon.social/tags/smallAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>smallAI</span></a></p>
Alasdair Allan<p>By me for <span class="h-card" translate="no"><a href="https://noc.social/@hackster_io" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>hackster_io</span></a></span>, "Deploying MobileNet on Microcontrollers," <a href="https://www.hackster.io/news/deploying-mobilenet-on-microcontrollers-31f2623ab383" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">hackster.io/news/deploying-mob</span><span class="invisible">ilenet-on-microcontrollers-31f2623ab383</span></a>. <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a></p>
Alasdair Allan<p>By me for <span class="h-card" translate="no"><a href="https://noc.social/@hackster_io" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>hackster_io</span></a></span>, “The beginnings of Small AI, <a href="https://www.hackster.io/news/the-beginnings-of-small-ai-64ef3768b7b5.”" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">hackster.io/news/the-beginning</span><span class="invisible">s-of-small-ai-64ef3768b7b5.”</span></a> <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> <a href="https://mastodon.social/tags/SmallAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SmallAI</span></a></p>
Shawn Hymel<p>The Google Coral Dev Board Micro is one powerful device 🦾🦾🦾 </p><p>Check out my latest video if you'd like to see how to get started using this board. Full object detection on 320x320 images at ~10 fps! <a href="https://masto.ai/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> <a href="https://masto.ai/tags/embedded" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>embedded</span></a> <a href="https://masto.ai/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a></p><p><a href="https://youtu.be/4KzWIJYnHW0" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/4KzWIJYnHW0</span><span class="invisible"></span></a></p>
Shawn Hymel<p>For the past couple of months, I've been working on a new set of features for the Edge Impulse Python SDK. You can now upload and download samples directly to/from your project! <a href="https://edgeimpulse.com/blog/announcing-new-python-sdk-features-upload-and-download-samples" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">edgeimpulse.com/blog/announcin</span><span class="invisible">g-new-python-sdk-features-upload-and-download-samples</span></a> <a href="https://masto.ai/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://masto.ai/tags/ML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ML</span></a> <a href="https://masto.ai/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> <a href="https://masto.ai/tags/Python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Python</span></a> <a href="https://masto.ai/tags/numpy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>numpy</span></a> <a href="https://masto.ai/tags/pandas" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pandas</span></a></p>
Alasdair Allan<p>Here we go! Depends how much of a purist you are whether you regard these as <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> or not. But you have to admit, it's <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> on a comparatively tight resource budget. <a href="https://arxiv.org/abs/2312.11514" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2312.11514</span><span class="invisible"></span></a></p>
Alasdair Allan<p>In today's mailbag, the second edition of the "TinyML Cookbook," by Gian Marco Iodice, <a href="https://amzn.to/47X6hTV" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">amzn.to/47X6hTV</span><span class="invisible"></span></a>. <a href="https://mastodon.social/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a></p>
Shawn Hymel<p>On deck to speak at <span class="h-card" translate="no"><a href="https://masto.ai/@hackaday" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>hackaday</span></a></span> <a href="https://masto.ai/tags/Supercon" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Supercon</span></a>! <a href="https://masto.ai/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a></p>
Shawn Hymel<p>I'm excited to be giving a talk at Hackaday's Supercon on my recent <a href="https://masto.ai/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> in <a href="https://masto.ai/tags/robotics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>robotics</span></a> project (spoiler: only a part of the "balancing" works). Other amazing speakers have been announced, including <span class="h-card" translate="no"><a href="https://chaos.social/@gella" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>gella</span></a></span>, <span class="h-card" translate="no"><a href="https://hachyderm.io/@stargirl" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>stargirl</span></a></span>, <span class="h-card" translate="no"><a href="https://infosec.exchange/@alexlynd" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>alexlynd</span></a></span>, and <span class="h-card" translate="no"><a href="https://mastodon.social/@poofjunior" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>poofjunior</span></a></span>! <a href="https://masto.ai/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> <a href="https://masto.ai/tags/engineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>engineering</span></a></p><p><a href="https://hackaday.com/2023/10/05/hackaday-superconference-2023-first-round-of-speakers-announced/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2023/10/05/hackad</span><span class="invisible">ay-superconference-2023-first-round-of-speakers-announced/</span></a></p>
Shawn Hymel<p>Does anyone have experience with ESP-DL? I'm trying to create a simple demo where I train a 2-layer DNN in PyTorch and convert it to ESP-DL code to run on my ESP32S3. If you have any insights, please let me know: <a href="https://github.com/espressif/esp-dl/issues/139" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/espressif/esp-dl/is</span><span class="invisible">sues/139</span></a> <a href="https://masto.ai/tags/ESP32" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ESP32</span></a> <a href="https://masto.ai/tags/microcontroller" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>microcontroller</span></a> <a href="https://masto.ai/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> <a href="https://masto.ai/tags/pytorch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pytorch</span></a></p>
Bose-Einstein-Kondensat<p>Low-cost <a href="https://mstdn.social/tags/air" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>air</span></a>, <a href="https://mstdn.social/tags/noise" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>noise</span></a> &amp; <a href="https://mstdn.social/tags/light" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>light</span></a> <a href="https://mstdn.social/tags/pollution" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pollution</span></a> measuring <a href="https://mstdn.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenSource</span></a> station with <a href="https://mstdn.social/tags/wireless" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>wireless</span></a> communication &amp; <a href="https://mstdn.social/tags/tinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tinyML</span></a>:<br><a href="https://sciencedirect.com/science/article/pii/S2468067223000846" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">sciencedirect.com/science/arti</span><span class="invisible">cle/pii/S2468067223000846</span></a><br><a href="https://mstdn.social/tags/DIYtech" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DIYtech</span></a> <a href="https://mstdn.social/tags/hackerspace" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hackerspace</span></a> <a href="https://mstdn.social/tags/SmartCity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SmartCity</span></a> <a href="https://mstdn.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://mstdn.social/tags/environment" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>environment</span></a> <a href="https://mstdn.social/tags/3Dprinted" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>3Dprinted</span></a> <a href="https://mstdn.social/tags/Arduino" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Arduino</span></a> <a href="https://mstdn.social/tags/ESP32" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ESP32</span></a></p>
Shawn Hymel<p>Doing some hardware hacking at the airport. I’m hoping to tinker with the neural network accelerator on the <a href="https://masto.ai/tags/ESP32" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ESP32</span></a> S3, and that’s only supported in ESP-IDF right now. Since I don’t know ESP-IDF very well, it’s time to skill up 💪 (and as always, start with blink 💡) <a href="https://masto.ai/tags/microcontroller" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>microcontroller</span></a> <a href="https://masto.ai/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a></p>
Shawn Hymel<p>New toy! <a href="https://masto.ai/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a></p>
Sebastian Büttrich @ ITU<p>"It s not gonna be the <a href="https://social.itu.dk/tags/computerscience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>computerscience</span></a> students, it s gonna be the <a href="https://social.itu.dk/tags/agriculture" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>agriculture</span></a> students"</p><p>^ ^ ^ !</p><p>Eric Pan of Seeed Studio at Abdus Salam International Centre for Theoretical Physics (ICTP) <a href="https://social.itu.dk/tags/TinyML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TinyML</span></a> workshop -</p><p>also stressing the importance of <a href="https://social.itu.dk/tags/LoRaWAN" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LoRaWAN</span></a> for the ecosystem.</p><p><a href="https://social.itu.dk/tags/IoT" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>IoT</span></a> in the <a href="https://social.itu.dk/tags/wild" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>wild</span></a></p>