axel180
Joined 8 years ago
Karma
29
Submissions
20
Member since
Oct 23
Recent submissions
Comment · 6 years ago
Comment · 7 years ago
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.
Comment · 7 years ago
Ty for your feedback. We'll be sure to use it if we make another.
Comment · 7 years ago
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/
Comment · 7 years ago
Also: https://github.com/gpujs/gpu.js
Note: this is what brain.js is shifting over to. It uses the... GPU.
Comment · 7 years ago
Really cool example!
Comment · 7 years ago
1. Tensorflow.js closely (not exactly) mirrors the python counterpart, and its api's, and thinking. We feel it does not reflect node ideologies well. And not the shify, what is in today is out tomorrow, thinking. The thinking that is practical, and applies well to business tastics. Brain.js started in node, and was original in its way it tackled the problem. Being data first, easy api, and then speed. It just works.
2. The vast majority of machine learning needs are encompassed within the library, and are only getting better.
3. The library can be learned in a matter of hours rather than weeks or months.
4. We can do it faster, simpler, than tensorflow.js. GPU support is coming in NodeJS, but is already partially implemented for browser, with fallback to CPU.
5. Brain.js was measured, where its benchmark was even better than industry standards, including IBM's Watson: https://github.com/jesus-seijas-sp/demo-nlp (note: project uses brain.js). Tensorflow.js isn't mentioned in this link, but I talked with the author about using Tensorflow.js, which he did try for this exact project, and his exact reply was: "with tensorflow.js same implementation I got a 0.91, but taked more time to train with CPU" (complete with typo)
6. Any corporation as powerful as those who maintain tensorflow should not have all the say in something as powerful as machine learning. Everyone should, and can.
7. We choose to.
Comment · 7 years ago
This was good, correct? I'd love to hear what your use case was, like which colors didn't work, etc.
Comment · 7 years ago
Ty for your thought. I'd love to know more specifics.
Comment · 7 years ago
That is really cool to hear!
Comment · 7 years ago
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.
Comment · 7 years ago
Ty, I hope my voice is/was not very irritating. I obsess over relaying ideas in a _very simple_ manner.
Things should be as simple as possible, but not simpler...
Comment · 7 years ago
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!
Comment · 7 years ago
Keep in mind that while the tutorial is in javascript, in the web browser, the neural network easily apply for node based solutions as well.
We're adding GPU support that use either client side OR server side GPU, so that any case you mention can be handled.
Comment · 7 years ago
Ty! This means a lot! Can you point me to the tutorial you added new tests with?
>I guess it's doing some sort of transformation
That is exactly correct. From javascript to an abstract syntax tree, and then to whatever target language we need. In this case GLSL.
>Presumably there's a not-significant overhead in both starting it up
That has been the goal, we're really careful to measure it with releases.
>and getting data back from the gpu.js function
That is correct as well, it is about as costly as it would be without GPU.js. However you can enable pipeline on kernels, so they can communicate via textures, which is significantly faster, as we don't need to transfer back to the CPU.
>Is there a way to "compile" a gpu.js function to remove the translation step? That could be really useful.
It is built into every kernel. You simply call `kernel.toString(...args)`.