Hacker News Reader

Comment by agibsonccc | Hacker News Reader

Polling for interest here for any neural net enthusiasts:

I'm the author of an open source distributed deep learning framework called deeplearning4j.

I am doing things with it such as sentiment analysis, face recognition, voice recognition,named entity recognition,...

I was considering creating a javascript visualizer for the tool (aka: train on the platform for the heavy lifting) then export the models to javascript for rendering and even in browser prediction.

How interesting would this be if it were implemented?

Thanks!

View on HN

Well, that explains it then. Thanks guys. That will be in the works. Since there's so much interest, I will also throw up a blog about the experience.

I'd definitely be interested! As long as we're wishing, I'd also like a Node.js module to do prediction on trained models. Your project looks really interesting, thank you!

Yes for sure. A node module will be in the works as well. My idea is to have this be a server akin to storm. I'll deal with the JVM, I'll just let you guys have fun ;).

Also: would just like to say, thank you for making my web development I've done over the past few years a delight.

How much horsepower do these things need?

Depends on how big the model is. The main problem with Deep Learning and practicality can be training time. For example, look here: http://www.deeplearning.net/tutorial/DBN.html

You'll notice at the bottom for the training time. That's immense.

The reason I'm encouraging horse power for practical use is to reduce training time to something meaningful for iteration use via distributed means.

I have visualization techniques built in to the lib to help come up with an optimal model so you know it works well, I still need to implement grid search and some other stuff.

My timeline is within the next month or so to have all of this done. I will have the stanford recursive neural tensor nets and the conv nets done here shortly. The next part will be distributed GPUs ;).

I hope to make this as practical as possible for people. The next obvious step after training time is practical and easy to do is wrappers for common tasks.

Can your library be used for OCR ?

Yes. That is one of the tutorials I give on the site. See the MNIST dataset. OCR is actually the hello world of deep learning.

Reply on news.ycombinator.com