Fork me on GitHub
Slack Archive

This page is not created by, affiliated with, or supported by Slack Technologies, Inc.

2017-09-28

Channels

#data-science
<
2017-09-28
>
rustam.gilaztdinov21:09:36

Hello, guys! So, we have such cool library called neanderthal. I see docs and think wow, seems like a magic troubleshooter for numbers crunching. And I want to implement a neural network. But docs so small and only one example in GitHub. How can I do this thing with neanderthal? I’m not so experienced programmer and this example not so clear 

(with-default-engine
  (with-release [gpu-x (cuv 1 -2 5)]
    (asum gpu-x)))
Should I every time call this ‘context’ ( assuming that is ‘context’ by function signature) to multiply matrices or not? Or can I create placeholders for values, or how I should calculate backprop and so on? If anyone shares an example, it will be super good. Or author adds more examples and docs. I want to use this library, but the barrier to entry is so high 😞 Thank you!