Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

aarushgupta.io

Post reply on HN
Print view View original

51–58 of 58 posts

Re: Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

#51

Post by ag2718 »

hansvm wrote: post #42
RantyDave wrote: post #3

Right. But ... this would limit you to either extremely small models or extremely large FPGA's, yes? If there's a simple machine learning task that requires a sub microsecond latency I can see the point but otherwise??

Yes, but simple models are far more expressive than people give them credit for. As one example, I've shoved Lots of image recognition tasks ( like spotting undesirable products in industrial settings), image modification tasks (I have some models locally to process hand-drawn images and unwarp them, remove notebook paper lines, etc), audio modification tasks (part of my editing pipeline includes hand-editing audio t…

Some very cool applications of small models! It seems that this scale of models tends to be sufficient when doing simpler classification, anomaly detection, signal processing, etc. as compared to generative modeling (where larger models are usually necessary).

Re: Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

#52

Post by jeffreysmith »

Super cool work. I love seeing this direction taken all the way to hardware.

I'm a big fan of KANs. The really seem like the start of something big and new. We've got a couple of papers out and in the works on KANs. The most relevant to OP's is this one: https://arxiv.org/abs/2512.15742v2

And we just put up a general primer on KANs on YT: https://youtu.be/wgcSsJ69x1c?si=fiUl1YGTgaTt_bn9 Fun stuff if you want to get into the weeds.

And if you are really interested in KANs, you should really check out Ziming (KAN creator)'s blog: https://kindxiaoming.github.io/blog/

Re: Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

#53

Post by UncleOxidant »

jeffreysmith wrote: post #52

Super cool work. I love seeing this direction taken all the way to hardware. I'm a big fan of KANs. The really seem like the start of something big and new. We've got a couple of papers out and in the works on KANs. The most relevant to OP's is this one: https://arxiv.org/abs/2512.15742v2 And we just put up a general primer on KANs on YT: https://youtu.be/wgcSsJ69x1c?si=fiUl1YGTgaTt_bn9 Fun stuff if you want to get i…

Searching around github and found someone has put up a github repo with a Julia implementation of the article here including FPGA implementation of a KAN MNIST classifier in Verilog. https://github.com/philtomson/KAN_LUT

Re: Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

#54

Post by ag2718 »

UncleOxidant wrote: post #53
jeffreysmith wrote: post #52

Super cool work. I love seeing this direction taken all the way to hardware. I'm a big fan of KANs. The really seem like the start of something big and new. We've got a couple of papers out and in the works on KANs. The most relevant to OP's is this one: https://arxiv.org/abs/2512.15742v2 And we just put up a general primer on KANs on YT: https://youtu.be/wgcSsJ69x1c?si=fiUl1YGTgaTt_bn9 Fun stuff if you want to get i…

Searching around github and found someone has put up a github repo with a Julia implementation of the article here including FPGA implementation of a KAN MNIST classifier in Verilog. https://github.com/philtomson/KAN_LUT

Our end-to-end implementation can be found here! https://github.com/Duchstf/KANELE

Re: Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

#55

Post by hansvm »

ag2718 wrote: post #51
hansvm wrote: post #42

Earlier quoted context omitted.

Yes, but simple models are far more expressive than people give them credit for. As one example, I've shoved Lots of image recognition tasks ( like spotting undesirable products in industrial settings), image modification tasks (I have some models locally to process hand-drawn images and unwarp them, remove notebook paper lines, etc), audio modification tasks (part of my editing pipeline includes hand-editing audio t…

Some very cool applications of small models! It seems that this scale of models tends to be sufficient when doing simpler classification, anomaly detection, signal processing, etc. as compared to generative modeling (where larger models are usually necessary).

Yep, as a rule of thumb generative models need to be much larger. As a small caveat, that's because of what we're doing with those models; generation itself can also be tiny and fast, but only when the output space is sufficiently constrained. Next-word prediction (in keyboards), speech codecs (TTS, especially for blind people), and a number of other scenarios both admit small models and fall into the domain of what most experts would call "generative."

Re: Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

#56

Post by scivizlabvienna »

andai wrote: post #49
scivizlabvienna wrote: post #45

I am using an almost identical architecture of a combination of lut-nn and bitnet on an upcoming fungal network interface which is basically just a metal pole rammed into the forest floor with electrodes at the bottom, fpga lut-nn in between and lora transceiver at the top. Thank you for this paper it will make pitching the concept alot easier using this as a reference :*

Explain like I'm mycelially challenged?

Avatar movie blue monkeys jack into forest matrix.

But the blue monkeys are metal rods with radio and the forest matrix are forest wide fungal colonies.

Re: Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

#57

Post by scivizlabvienna »

andai wrote: post #49
scivizlabvienna wrote: post #45

I am using an almost identical architecture of a combination of lut-nn and bitnet on an upcoming fungal network interface which is basically just a metal pole rammed into the forest floor with electrodes at the bottom, fpga lut-nn in between and lora transceiver at the top. Thank you for this paper it will make pitching the concept alot easier using this as a reference :*

Explain like I'm mycelially challenged?

https://host-html.com/p/funginet

Re: Ultrafast machine learning on FPGAs via Kolmogorov-Arnold Networks

#58

Post by ag2718 »

bjourne wrote: post #50

Sorry, I haven't had time to read your papers in full yet. Have you considered that LUTs on many FPGAs aren't 2:1 but instead, say, 6:3 and also may contain flip-flops and muxes? FPGA synthesis may not be as easy as "just" translating the activation functions to LUTs.

This is a simplification in the blog post: each activation doesn't map one-to-one onto a physical FPGA LUT primitive, but is instead represented as a "logical LUT" (L-LUT) that Vivado synthesizes into distributed RAM. These L-LUTs map very naturally to FPGA fabric (as compared to multiply-accumulate operations), making them a very useful implementation-level abstraction.
Post reply on HN