<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>paper on The Site of laekov</title>
    <link>/tags/paper/</link>
    <description>Recent content in paper on The Site of laekov</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>&amp;copy; laekov</copyright>
    <lastBuildDate>Mon, 09 Jul 2018 11:38:28 +0000</lastBuildDate><atom:link href="/tags/paper/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>DyNet 论文笔记</title>
      <link>/technical/e51049/</link>
      <pubDate>Mon, 09 Jul 2018 11:38:28 +0000</pubDate>
      
      <guid>/technical/e51049/</guid>
      <description>DYNET 1701.03980
ABS cpp backend
lw graph representation
Problems easier debugging / maintaining large proj. express naturally Static vs Dynamic static pre-written model transfered to computation graph
graph can be well optimized
cannot deal with variable input size. NLP RNN
cannot deal with variable input structure. Tree NN, Graph NN
hard for complex flow-contronl logic (interface design)
nontrivial interface.
debug difficulty during execution
dynamic do computation on the fly
can be expensiveo flow control and variable sized inputs are in host language (python?</description>
    </item>
    
  </channel>
</rss>
