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

Brain.js

github.com

Post reply on HN
Print view View original

51–56 of 56 posts

Re: Brain.js

#51

Post by WrtCdEvrydy »

axel180 wrote: post #22
WrtCdEvrydy wrote: post #12

Earlier quoted context omitted.

For reference, NodeJS support for GPUs will only drop under version 2, so if you're planning on GPU acceleration, this is not for you.

This is Robert, the lead developer for brain.js. Ty for the plug! I was going to mention this, nice to see people listening and helping spread the word. Working on it hard guys! When spare time cannot be had, just stay up late, and get up early!

This is not to mean that it's not a useful tool for teaching people simplified neural networks without having to whip out a full tensorflow environment.

Edit: When you have a working 2.0 beta, do you mind if I build a docker-jupyter notebook kinda like the Tensorflow docker? Something with nvidia-docker runtime on jupyter-nodejs? I really just wanna bring this into a more mainstream audience.

Re: Brain.js

#52

Post by axel180 »

gammateam wrote: post #49
revskill wrote: post #35

JS nails it again even with Neuron Networks. What saddens me in latest years is the direction of library development, where people put more focus on Python instead of Javascript. Javascript is universal, you can reuse your code in both browser, native apps and server. Python ? I don't think so. My dream of "getting the job done" is a universal language, universal ecosystem/libraries. We need universal developers, no…

I couldn't really understand how the JS community is so vibrant in some areas and flocks to libraries every other day, but the python community gravitated around all the big data stuff Not saying it shouldn't, I just don't get the aberration given the computational resources available today since compute instances mitigate single event loop issues Is there a JS version of numpy and panda? edit: yes, there are https:/…

Also: https://github.com/gpujs/gpu.js

Note: this is what brain.js is shifting over to. It uses the... GPU.

Re: Brain.js

#53

Post by vorticalbox »

danielmorozoff wrote: post #8

Can someone comment on performance -- speed vs training vs other frameworks. Most of our work is in TF/Pytorch and I have not used any JS implementations would love to hear some peoples insights into how it compares.

I just did the maths one.

1 to 10 addition, 2000 iterations took about 5 mins on repl.it

It got the maths wrong so will need more training

Re: Brain.js

#54

Post by axel180 »

WrtCdEvrydy wrote: post #51
axel180 wrote: post #22

Earlier quoted context omitted.

This is Robert, the lead developer for brain.js. Ty for the plug! I was going to mention this, nice to see people listening and helping spread the word. Working on it hard guys! When spare time cannot be had, just stay up late, and get up early!

This is not to mean that it's not a useful tool for teaching people simplified neural networks without having to whip out a full tensorflow environment. Edit: When you have a working 2.0 beta, do you mind if I build a docker-jupyter notebook kinda like the Tensorflow docker? Something with nvidia-docker runtime on jupyter-nodejs? I really just wanna bring this into a more mainstream audience.

That'd be awesome!

I've used: https://github.com/n-riesco/ijavascript https://github.com/notablemind/jupyter-nodejs

Or even: https://beta.observablehq.com/

Re: Brain.js

#55

Post by axel180 »

Etheryte wrote: post #41
axel180 wrote: post #26

Earlier quoted context omitted.

Ty for your thought. I'd love to know more specifics.

Most of the arguments either don't add up (e.g. saying it's mathematically proven while ML doesn't have rigorous theory) or are too generic to add much value. The course feels more like a verbal introduction to the library API rather than teaching anything related to ML.

Ty for your feedback. We'll be sure to use it if we make another.

Re: Brain.js

#56

Post by axel180 »

spiffytech wrote: post #34
axel180 wrote: post #24

Earlier quoted context omitted.

What happened was essentially bullies. I think it is apparent now that the library and, more importantly, the idea of a data first neural network architecture in javascript isn't going away.

What do you mean by "data-first"? What other forms could a JS NN architecture take?

A lot of neural networks start by first constructing the neural network structure, and eventually getting around to running the data through it. Where in brain.js, line 2 in most examples (just after instantiation) is train with data.
Post reply on HN