<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Neural Networks on Going the distance</title>
    <link>https://jeiwan.net/tags/neural-networks/</link>
    <description>Recent content in Neural Networks on Going the distance</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <lastBuildDate>Sat, 05 Aug 2017 20:34:21 +0700</lastBuildDate><atom:link href="https://jeiwan.net/tags/neural-networks/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>TIL: Convolutional Filters Are Weights</title>
      <link>https://jeiwan.net/posts/til-convolution-filters-are-weights/</link>
      <pubDate>Sat, 05 Aug 2017 20:34:21 +0700</pubDate>
      
      <guid>https://jeiwan.net/posts/til-convolution-filters-are-weights/</guid>
      <description>It&amp;rsquo;s common knowledge that there&amp;rsquo;re weights in a fully-connected neural network. And these weights are not constant and are adjusted by an optimization algorithm (like gradient descent). Moreover, training a neural network actually means finding proper weights.
When I started learning about convolution and convolutional networks, first thing I was introduced to is filters. Filters are said to be matrices that are applied to an image to distort it in a certain way, unveiling certain aspect of an image.</description>
    </item>
    
  </channel>
</rss>
