<?xml version="1.0" encoding="UTF-8"?><!-- generator="wordpress/2.3.3" -->
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	>
<channel>
	<title>Comments on: GOCR to Neural Nets Pt 2</title>
	<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/</link>
	<description>SEO Tools. I code 'em.</description>
	<pubDate>Thu, 28 Aug 2008 18:18:20 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.3.3</generator>
		<item>
		<title>By: Michael</title>
		<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-697</link>
		<dc:creator>Michael</dc:creator>
		<pubDate>Wed, 04 Jun 2008 06:58:57 +0000</pubDate>
		<guid>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-697</guid>
		<description>Just wondering when training ... does it have to be done on different captchas or just one?  I have it working on my training captcha, but not even close on another with out training. Seems once I start trainging on multiple captchas, when in 0 mode it takes forever.  Any ideas would be appreciated thanks.</description>
		<content:encoded><![CDATA[<p>Just wondering when training &#8230; does it have to be done on different captchas or just one?  I have it working on my training captcha, but not even close on another with out training. Seems once I start trainging on multiple captchas, when in 0 mode it takes forever.  Any ideas would be appreciated thanks.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Dark SEO Programming &#187; Blog Archive &#187; Instant GOCR Training</title>
		<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-207</link>
		<dc:creator>Dark SEO Programming &#187; Blog Archive &#187; Instant GOCR Training</dc:creator>
		<pubDate>Wed, 16 Apr 2008 19:22:39 +0000</pubDate>
		<guid>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-207</guid>
		<description>[...] The first entry is the filename, and it can literally be any pbm/png file. The second entry is the correct letter. That simple. All we have to do is rip the letters out and put them in the same directory. Unfortunately I haven&#8217;t got the script cleaned in a nice easy to use format to just download, but I&#8217;ll post what I used to build my custom database very quickly. I use the retrieve.php include which is somewhere on this site. I should be more organised. I think it&#8217;s here. [...]</description>
		<content:encoded><![CDATA[<p>[&#8230;] The first entry is the filename, and it can literally be any pbm/png file. The second entry is the correct letter. That simple. All we have to do is rip the letters out and put them in the same directory. Unfortunately I haven&#8217;t got the script cleaned in a nice easy to use format to just download, but I&#8217;ll post what I used to build my custom database very quickly. I use the retrieve.php include which is somewhere on this site. I should be more organised. I think it&#8217;s here. [&#8230;]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Insomnia</title>
		<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-122</link>
		<dc:creator>Insomnia</dc:creator>
		<pubDate>Wed, 02 Apr 2008 01:48:25 +0000</pubDate>
		<guid>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-122</guid>
		<description>Gah, PHP is such a pain in the butt to learn lol, so I think I'll stick with my html for now. But you're definately not a bad writer.</description>
		<content:encoded><![CDATA[<p>Gah, PHP is such a pain in the butt to learn lol, so I think I&#8217;ll stick with my html for now. But you&#8217;re definately not a bad writer.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: anty</title>
		<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-119</link>
		<dc:creator>anty</dc:creator>
		<pubDate>Mon, 31 Mar 2008 17:11:16 +0000</pubDate>
		<guid>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-119</guid>
		<description>Inspired by your first post, I tried this ANN coded in PHP entirely: http://www.tremani.nl/open-source/neural-network/

I don't know how the speed compares to other ANNs, but it's pretty simple to use once, you know what ANNs are :)</description>
		<content:encoded><![CDATA[<p>Inspired by your first post, I tried this ANN coded in PHP entirely: <a href="http://www.tremani.nl/open-source/neural-network/" rel="nofollow">http://www.tremani.nl/open-source/neural-network/</a></p>
<p>I don&#8217;t know how the speed compares to other ANNs, but it&#8217;s pretty simple to use once, you know what ANNs are <img src='http://www.darkseoprogramming.com/wp-includes/images/smilies/icon_smile.gif' alt=':)' class='wp-smiley' /></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Dedicated-server.net</title>
		<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-118</link>
		<dc:creator>Dedicated-server.net</dc:creator>
		<pubDate>Mon, 31 Mar 2008 10:20:33 +0000</pubDate>
		<guid>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-118</guid>
		<description>Hmm.. He is a better writer. I agree with that.</description>
		<content:encoded><![CDATA[<p>Hmm.. He is a better writer. I agree with that.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Harry</title>
		<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-116</link>
		<dc:creator>Harry</dc:creator>
		<pubDate>Mon, 31 Mar 2008 08:29:28 +0000</pubDate>
		<guid>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-116</guid>
		<description>I most definitely am over complicating things. You could have just used GOCR or phpOCR and got the same results. It's just interesting to learn loads of different techniques.

You might find that neural nets come in more useful somewhere else... You never know.

I was actually thinking about neuro-evolution, and evolutionary programming the other day. And it crossed my mind that the two are very similar. In many ways the neuron weights are like a statement of code. I think you can do more with a neural network than you could imagine, it's just that initial training it and getting the correct number of layers so it can store enough information about the pattern but not so much it takes a million years to train. Hmmm...</description>
		<content:encoded><![CDATA[<p>I most definitely am over complicating things. You could have just used GOCR or phpOCR and got the same results. It&#8217;s just interesting to learn loads of different techniques.</p>
<p>You might find that neural nets come in more useful somewhere else&#8230; You never know.</p>
<p>I was actually thinking about neuro-evolution, and evolutionary programming the other day. And it crossed my mind that the two are very similar. In many ways the neuron weights are like a statement of code. I think you can do more with a neural network than you could imagine, it&#8217;s just that initial training it and getting the correct number of layers so it can store enough information about the pattern but not so much it takes a million years to train. Hmmm&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ozonew4m</title>
		<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-115</link>
		<dc:creator>ozonew4m</dc:creator>
		<pubDate>Sun, 30 Mar 2008 23:20:04 +0000</pubDate>
		<guid>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-115</guid>
		<description>oh yeah.. and you are a better writer than you think you are!!</description>
		<content:encoded><![CDATA[<p>oh yeah.. and you are a better writer than you think you are!!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ozonew4m</title>
		<link>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-114</link>
		<dc:creator>ozonew4m</dc:creator>
		<pubDate>Sun, 30 Mar 2008 23:18:53 +0000</pubDate>
		<guid>http://www.darkseoprogramming.com/2008/03/30/gocr-to-neural-nets-pt-2/#comment-114</guid>
		<description>I think you are over complicating things a tad... Im no expert at breaking capchas, in fact i never even thought of trying until i read your phpbb2 capcha post..

Ive since got to work using only php and the gd library to clean and crop the images and using a php class to solve them..

admittadly im only working on the phpbb2 captcha but ive got it up to 91% success rate and its pretty quick...

anyway.. keep the posts coming your approaches are very interesting.. like i said im new to this stuff so all info is good info</description>
		<content:encoded><![CDATA[<p>I think you are over complicating things a tad&#8230; Im no expert at breaking capchas, in fact i never even thought of trying until i read your phpbb2 capcha post..</p>
<p>Ive since got to work using only php and the gd library to clean and crop the images and using a php class to solve them..</p>
<p>admittadly im only working on the phpbb2 captcha but ive got it up to 91% success rate and its pretty quick&#8230;</p>
<p>anyway.. keep the posts coming your approaches are very interesting.. like i said im new to this stuff so all info is good info</p>
]]></content:encoded>
	</item>
</channel>
</rss>
