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

Tinygrad: A simple and powerful neural network framework

tinygrad.org

Post reply on HN
Print view View original

11–20 of 147 posts

Re: Tinygrad: A simple and powerful neural network framework

#11

Post by DeathArrow »

jack_pp wrote: post #8
DeathArrow wrote: post #3

I believe neural networks are over hyped sometimes. They are not always the best tool for the job. There are lots of other ML techniques such as SVM, naive Bayes, k-nearest neighbor, decision tree, logistic regression, random forest etc. nobody is using because they lack the hype factor. If something lacks some keywords like neural network, deep learning, reinforced learning, than it is deemed not cool.

I'm no expert but can you show how those techniques can be used to solve the same problems NNs can? Like SOTA image recognition, chess / go, STT, TTS etc?

>I'm no expert but can you show how those techniques can be used to solve the same problems NNs can?

Sentiment analysis, classification.

Re: Tinygrad: A simple and powerful neural network framework

#12

Post by zelphirkalt »

learndeeply wrote: post #6
DeathArrow wrote: post #3

I believe neural networks are over hyped sometimes. They are not always the best tool for the job. There are lots of other ML techniques such as SVM, naive Bayes, k-nearest neighbor, decision tree, logistic regression, random forest etc. nobody is using because they lack the hype factor. If something lacks some keywords like neural network, deep learning, reinforced learning, than it is deemed not cool.

I can't think of anything that neural nets can't beat, except small tabular data with boosted decision trees. Can you give some examples?

Explicability is a big part of it It is often worth being a percent less accurat but having an explainable result.

Re: Tinygrad: A simple and powerful neural network framework

#13

Post by _0nel »

matesz wrote: post #9

If anybody is dealing with procrastination watch George Hotz live streaming 10h straight working on this library [1][2]. Does he take some supplements to do this? There is even 19.5h stream [3]. Actually I have local obs setup to record myself, just instead of streaming I do recordings for my own inspection. Important part is to do the inspection after. It works wonders. [1] https://youtu.be/GXy5eVwnL_Q [2] https://m…

yeah man he does, but he is crazy genius like Nikola Tesla or something and I’m not

Re: Tinygrad: A simple and powerful neural network framework

#14

Post by patrick451 »

learndeeply wrote: post #6
DeathArrow wrote: post #3

I believe neural networks are over hyped sometimes. They are not always the best tool for the job. There are lots of other ML techniques such as SVM, naive Bayes, k-nearest neighbor, decision tree, logistic regression, random forest etc. nobody is using because they lack the hype factor. If something lacks some keywords like neural network, deep learning, reinforced learning, than it is deemed not cool.

I can't think of anything that neural nets can't beat, except small tabular data with boosted decision trees. Can you give some examples?

The black box nature of a neural net is a problem. For model based design, a bit more accuracy out of a black box doesn't really help when you need, for example, state space matrices in a control design.

Re: Tinygrad: A simple and powerful neural network framework

#17

Post by pyinstallwoes »

matesz wrote: post #9

If anybody is dealing with procrastination watch George Hotz live streaming 10h straight working on this library [1][2]. Does he take some supplements to do this? There is even 19.5h stream [3]. Actually I have local obs setup to record myself, just instead of streaming I do recordings for my own inspection. Important part is to do the inspection after. It works wonders. [1] https://youtu.be/GXy5eVwnL_Q [2] https://m…

If it's not Adderall I don't know. But, if I've ever focused for that long it's been because of Ritalin or Adderall.

Re: Tinygrad: A simple and powerful neural network framework

#18

Post by kklisura »

sakras wrote: post #7

I must say they gained instant credibility with the minimalistic website given how fast it loaded. Code looks simple and easy to follow, and I love how the comments are constantly mentioning hardware characteristics, making maxing the hardware the goal. It seems that it’s trying to achieve this by jitting optimal code for the operations at hand rather than hand-optimizing kernels, and betting that the small number of…

It's geohot. He comes with credibility. [1]

[1] https://en.wikipedia.org/wiki/George_Hotz

Re: Tinygrad: A simple and powerful neural network framework

#19

Post by niemandhier »

learndeeply wrote: post #6
DeathArrow wrote: post #3

I believe neural networks are over hyped sometimes. They are not always the best tool for the job. There are lots of other ML techniques such as SVM, naive Bayes, k-nearest neighbor, decision tree, logistic regression, random forest etc. nobody is using because they lack the hype factor. If something lacks some keywords like neural network, deep learning, reinforced learning, than it is deemed not cool.

I can't think of anything that neural nets can't beat, except small tabular data with boosted decision trees. Can you give some examples?

Small data problems, where’re never the less have a really good idea of how things are causally related.

Re: Tinygrad: A simple and powerful neural network framework

#20

Post by kklisura »

pyinstallwoes wrote: post #17
matesz wrote: post #9

If anybody is dealing with procrastination watch George Hotz live streaming 10h straight working on this library [1][2]. Does he take some supplements to do this? There is even 19.5h stream [3]. Actually I have local obs setup to record myself, just instead of streaming I do recordings for my own inspection. Important part is to do the inspection after. It works wonders. [1] https://youtu.be/GXy5eVwnL_Q [2] https://m…

If it's not Adderall I don't know. But, if I've ever focused for that long it's been because of Ritalin or Adderall.

I think it's combination of: 1) he's really passionate about what he's doing 2) he sees the problem as real challenge 3) he doesn't have corporate structure on his back giving him deadlines and pressure
Post reply on HN