TinyML: Ultra-low power machine learning

#1

Post by Gedxx » Tue, Jan 16, 2024, 4:03 PM UTC

TinyML: Ultra-low power machine learning
ikkaro.net

Re: TinyML: Ultra-low power machine learning

#2

Post by orliesaurus » Tue, Jan 16, 2024, 4:54 PM UTC

Cool title - but what's/where's a demo showing how this is applied in the real world?

Re: TinyML: Ultra-low power machine learning

#3

Post by andy99 » Tue, Jan 16, 2024, 5:10 PM UTC

I'm really surprised TF lite is being used. Do they train models or is this (my assumption) just inference? Do they have a talent constraint? I would have expected handwritten C inference in order to make these as small and efficient as possible.

Re: TinyML: Ultra-low power machine learning

#4

Post by synergy20 » Tue, Jan 16, 2024, 5:14 PM UTC

andy99 wrote: post #3

I'm really surprised TF lite is being used. Do they train models or is this (my assumption) just inference? Do they have a talent constraint? I would have expected handwritten C inference in order to make these as small and efficient as possible.

it's all inference

Re: TinyML: Ultra-low power machine learning

#5

Post by synergy20 » Tue, Jan 16, 2024, 5:17 PM UTC

TinyML is like IoT: great on concepts, everyone agrees it's the future, but has been slow to take off.

or, maybe it's just that they're being built into all products now, they just do not need the brand for them such as IoT or TinyML.

Re: TinyML: Ultra-low power machine learning

#6

Post by cyberninja15 » Tue, Jan 16, 2024, 5:23 PM UTC

synergy20 wrote: post #4

andy99 wrote: post #3

I'm really surprised TF lite is being used. Do they train models or is this (my assumption) just inference? Do they have a talent constraint? I would have expected handwritten C inference in order to make these as small and efficient as possible.

it's all inference

Makes sense. And, TF Lite is excellent for on-device models and inference.

Re: TinyML: Ultra-low power machine learning

#7

Post by modeless » Tue, Jan 16, 2024, 5:28 PM UTC

synergy20 wrote: post #5

TinyML is like IoT: great on concepts, everyone agrees it's the future, but has been slow to take off. or, maybe it's just that they're being built into all products now, they just do not need the brand for them such as IoT or TinyML.

I don't agree that TinyML is the future, just as I don't think IoT is the future. The future is robot servants. They will be ~human scale and have plenty of power to run regular big ML.

In fact, I hope my home has fewer smart devices in the future. I don't need an electronic door lock if my robot butler unlocks the door when I get home. I don't need smart window shades if the butler opens and closes them whenever I want. I don't need a dishwasher or bread maker or Cuisinart or whatever other labor saving device if I don't need to save labor anymore. Labor will be practically free.

Re: TinyML: Ultra-low power machine learning

#8

Post by _joel » Tue, Jan 16, 2024, 5:32 PM UTC

For those looking for some more content, there's a bunch of videos from their Asia 2023 conference. https://www.tinyml.org/event/asia-2023/

- Target Classification on the Edge using mmWave Radar: A Novel Algorithm and Its Real-Time Implementation on TI’s IWRL6432 (Muhammet Emin YANIK) https://www.youtube.com/watch?v=SNNhUT_V8vM

Re: TinyML: Ultra-low power machine learning

#9

Post by synergy20 » Tue, Jan 16, 2024, 5:32 PM UTC

modeless wrote: post #7

synergy20 wrote: post #5

TinyML is like IoT: great on concepts, everyone agrees it's the future, but has been slow to take off. or, maybe it's just that they're being built into all products now, they just do not need the brand for them such as IoT or TinyML.

I don't agree that TinyML is the future, just as I don't think IoT is the future. The future is robot servants. They will be ~human scale and have plenty of power to run regular big ML. In fact, I hope my home has fewer smart devices in the future. I don't need an electronic door lock if my robot butler unlocks the door when I get home. I don't need smart window shades if the butler opens and closes them whenever I w…

I consider tinyml is like an ant or a spider, it's tiny, but intelligent enough to do its own inference to survive. not all insects and animals need plenty of power to exist, so do AI agents, so yes TinyML has its places, in fact maybe way more than where the powerful AI agents are needed.

Re: TinyML: Ultra-low power machine learning

#10

Post by oytis » Tue, Jan 16, 2024, 5:33 PM UTC

modeless wrote: post #7

synergy20 wrote: post #5

TinyML is like IoT: great on concepts, everyone agrees it's the future, but has been slow to take off. or, maybe it's just that they're being built into all products now, they just do not need the brand for them such as IoT or TinyML.

I don't agree that TinyML is the future, just as I don't think IoT is the future. The future is robot servants. They will be ~human scale and have plenty of power to run regular big ML. In fact, I hope my home has fewer smart devices in the future. I don't need an electronic door lock if my robot butler unlocks the door when I get home. I don't need smart window shades if the butler opens and closes them whenever I w…

If labor is free, what are you going to pay for a servant robot with? Why would robots serve useless humans?