#TinyML

Doug Ortizdougortiz
2025-03-07

๐ŸŒ Can AI Fit on a Microchip?

TinyML Proves It!

๐Ÿ”ฅ Why it's revolutionary:
โšก Real-time processing
๐Ÿ”‹ 10x energy efficiency
๐Ÿ”’ Data never leaves your device

๐ŸŒพ Farm sensors โ†’ predicts crop health
๐Ÿฅ Medical wearables โ†’ instant diagnostics
๐Ÿญ Smart factories โ†’ self-repairing machines

Spoiler: It's already here. ๐Ÿ‘€

Boost to spread the micro-revolution! ๐Ÿš€

Watch now: link.illustris.org/tinyml

Doug Ortizdougortiz
2025-02-10

๐Ÿค–โœจ TinyML: Big AI, Zero Cloud โœจ

๐ŸŒฑ Why cloud dependence? processes data locally on microcontrollers:

๐Ÿฉบ Privacy-first health monitors
๐Ÿญ Predictive maintenance (40% downtime cut)
โšก๏ธ Open-source tools @EdgeImpulse @tensorflow

Build with Arduino Nano/Raspberry Pi! ๐Ÿ’ป

Full video: link.illustris.org/tinyml

โšก๏ธBoost

choaschoas
2024-12-30

Super excited to share that Iโ€™ll be speaking at PyCon+Web 2025 on January 25th in Berlin! ๐ŸŽคโœจ My talk, "๐—˜๐—ฑ๐—ด๐—ฒ ๐—”๐—œ ๐˜„๐—ถ๐˜๐—ต ๐— ๐—ถ๐—ฐ๐—ฟ๐—ผ๐—ฃ๐˜†๐˜๐—ต๐—ผ๐—ป ๐—ฎ๐—ป๐—ฑ ๐—ง๐—ฒ๐—ป๐˜€๐—ผ๐—ฟ๐—™๐—น๐—ผ๐˜„ ๐—ณ๐—ผ๐—ฟ ๐— ๐—ถ๐—ฐ๐—ฟ๐—ผ๐—ฐ๐—ผ๐—ป๐˜๐—ฟ๐—ผ๐—น๐—น๐—ฒ๐—ฟ" is going to dive into the fascinating world where AI meets tiny tech.

It's like fitting an elephant or mammoth into a shoebox! ๐Ÿ˜๐Ÿ“ฆ

Canโ€™t wait to meet all the amazing Python and web enthusiastsโ€”letโ€™s make it awesome! ๐ŸŽ‰

Details here: pyconweb.com/activity/edge-ai-

2024-11-24

I wrote a #rust crate Moden Hopfield Network. I used it to build a neural network that can be trained on the edge. See the demo linked in the README.md.

Modern Hopfield Network has much (much) larger capacity than classical Hopfield Network. They are also called Dense Associative Memory.

#holfield-network #tinyml

github.com/dilawar/moden-hopfi

Explore how #TinyML is revolutionizing edge computing by deploying #MachineLearning models on ultra-low-power devices.

Dive into the challenges of optimizing memory, power consumption, and real-time processing in constrained environments: ter.li/ndjs0l

2024-07-05

Help us out by simply clicking the star โญ๏ธ button on this repo: github.com/harvard-edge/cs249r For every 25 stars this open source #TinyML textbook repo gets, @seeedstudio a hardware kit to a school. #Arduino #ESP32 #education #STEM #AI

Alasdair Allanaallan
2024-07-04

Huh! Just stumbled across the Analog Devices MAX78000. It's a Cortex M4F with an on-chip CNN accelerator. This looks rather interesting, github.com/analogdevicesinc/Ma. Anyone had a play? How's the development toolchain?

2024-06-25

#neuromorphic computing and spiking neural networks promise orders of magnitude better energy efficiency than their artificial NN counterparts running on CPUs and GPUs. But weโ€™re still struggling to make SNNs perform as good as ANNs on similar tasks. #AI #TinyML #MachineLearning

Alasdair Allanaallan
2024-06-24

Another interesting example of mixture-of-agents architectures, this one from the folks at combining and at the edge. edgeimpulse.com/blog/using-llm

Alasdair Allanaallan
2024-06-12

By me for @hackster_io, "The CH32, just another 10ยข microcontroller?" The latest project to appear for the 10ยข CH32 RISC-V microcontroller is a tiny wake word engine with impressive accuracy levels. hackster.io/news/the-ch32-just

2024-06-11

A few days ago I worked out a way of representing neural networks in Rust's type system via const generics and then that lead me to making a neural network library that doesn't use the standard library or any heap allocation, then that lead me to today where I have a pre-trained neural network running on an ATtiny85 approximating the output of an XOR gate, I'm in no way a very good data scientist or embedded engineer at all so the fact I managed to get a neural network running on an 1MHz 8 bit chip with 8k of program memory with 512 BYTES of ram, all whilst doing almost zero optimisations is insane to me

github.com/jasonalexander-ja/m

#rust #rustlang #tinyml #embedded

Alasdair Allanaallan
2024-06-07

By me for @hackster_io, "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. hackster.io/news/benchmarking-

Alasdair Allanaallan
2024-05-31
Alasdair Allanaallan
2024-05-30

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst