I hereby claim:
- I am ixtel on github.
- I am ixtel (https://keybase.io/ixtel) on keybase.
- I have a public key ASCWp9Jd7mzC6x6RE-iVMLVwNK7zYkLL4MMcez-6OMDhNQo
To claim this, I am signing this object:
I hereby claim:
To claim this, I am signing this object:
<!DOCTYPE html> | |
<html> | |
<head> | |
<link href="http://getbootstrap.com/2.3.2/assets/css/bootstrap.css" rel="stylesheet" type="text/css" /> | |
<link href="http://getbootstrap.com/2.3.2/assets/css/bootstrap-responsive.css" rel="stylesheet" type="text/css" /> | |
<script src="http://cdnjs.cloudflare.com/ajax/libs/knockout/2.2.1/knockout-min.js"></script> | |
<meta charset=utf-8 /> | |
<title>JS Bin</title> |
A comparison of Theano with other deep learning frameworks, highlighting a series of low-level design choices in no particular order.
Overview
Symbolic: Theano, CGT; Automatic: Torch, MXNet
Symbolic and automatic differentiation are often confused or used interchangeably, although their implementations are significantly different.