byzhang

A comparison of Theano with other deep learning frameworks, highlighting a series of low-level design choices in no particular order.

Overview

• Differentiation

Differentiation

Symbolic: Theano, CGT; Automatic: Torch, MXNet

Symbolic and automatic differentiation are often confused or used interchangeably, although their implementations are significantly different.

byzhang

Install Boost1.53 on Centos with PUIAS

Create puias-computational.repo file:

$ vim /etc/yum.repos.d/puias-computational.repo

Paste the following code into the above file:

byzhang

import urllib2
from lxml import html
from collections import defaultdict

url   = "http://www.youtube.com/watch?v=IyLZ6RXJ8Eg"
doc   = html.parse(urllib2.urlopen(url))
data  = defaultdict(dict)
props = doc.xpath('//meta[re:test(@name|@property, "^twitter|og:.*$", "i")]',
                  namespaces={"re": "http://exslt.org/regular-expressions"})