<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Ben Bogart - Art &#38; Ideas &#187; Dreaming Machine</title>
	<atom:link href="http://www.ekran.org/ben/wp/category/production/dreaming-machine/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.ekran.org/ben/wp</link>
	<description>Electronic Media Art by Ben Bogart</description>
	<lastBuildDate>Tue, 31 Jan 2012 20:34:26 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
		<item>
		<title>Reconstruction of image from segmented chunks from multiple frames</title>
		<link>http://www.ekran.org/ben/wp/2012/reconstruction-of-image-from-segmented-chunks-from-multiple-frames/</link>
		<comments>http://www.ekran.org/ben/wp/2012/reconstruction-of-image-from-segmented-chunks-from-multiple-frames/#comments</comments>
		<pubDate>Mon, 09 Jan 2012 23:47:33 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1284</guid>
		<description><![CDATA[Above is a reconstruction of approximately 20 frames of video test footage. The reconstruction is composed of the perceptual chunks that were segmented (as described in previous posts). White areas are areas where no segmentation was performed. So far this just looks like a normal long exposure, but things should get more aesthetically interesting once [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2012/reconstruction-of-image-from-segmented-chunks-from-multiple-frames/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Segmentation Update</title>
		<link>http://www.ekran.org/ben/wp/2011/segmentation-update/</link>
		<comments>http://www.ekran.org/ben/wp/2011/segmentation-update/#comments</comments>
		<pubDate>Sat, 10 Dec 2011 01:21:15 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1276</guid>
		<description><![CDATA[I wanted to post my progress on segmentation before I start working on clustering and video sequences. Here are images that show the current state of segmentation (down to under 2s per frame) of a more realistic Vancouver scene captured on video: (reconstruction, mean-shift filtering, original image) Current state of the code: 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298#include &#34;opencv2/highgui/highgui.hpp&#34; #include [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/segmentation-update/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Segmentation with OpenCV GPU</title>
		<link>http://www.ekran.org/ben/wp/2011/segmentation-with-opencv-gpu/</link>
		<comments>http://www.ekran.org/ben/wp/2011/segmentation-with-opencv-gpu/#comments</comments>
		<pubDate>Sat, 26 Nov 2011 22:40:22 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1270</guid>
		<description><![CDATA[In playing with code for deep learning (DBNs in particular) I&#8217;ve had to install CUDA to do matrix processing on the GPU. So I went ahead and recompiled openCV to use CUDA. Following is a similar segmentation image to the one in previous posts. This one was computed in 2.7s on the GPU, and on [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/segmentation-with-opencv-gpu/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Global Workspace Theory, Free Will and The Location of Mental Images.</title>
		<link>http://www.ekran.org/ben/wp/2011/global-workspace-theory-free-will-and-the-location-of-mental-images/</link>
		<comments>http://www.ekran.org/ben/wp/2011/global-workspace-theory-free-will-and-the-location-of-mental-images/#comments</comments>
		<pubDate>Fri, 11 Nov 2011 19:32:19 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1244</guid>
		<description><![CDATA[I&#8217;m continuing to listen to some of Franklin&#8217;s lectures about LIDA and cognitive modelling in general. Yesterday I got through the one explaining Global Workspace Theory (GWT). Little did I know, but I had already come across this theory during my Masters research, and discounted it due to its causal disconnection between consciousness and cognitive [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/global-workspace-theory-free-will-and-the-location-of-mental-images/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>First Attempt to Integrate LIDA and current DM3 thinking.</title>
		<link>http://www.ekran.org/ben/wp/2011/first-attempt-to-integrate-lida-and-current-dm3-thinking/</link>
		<comments>http://www.ekran.org/ben/wp/2011/first-attempt-to-integrate-lida-and-current-dm3-thinking/#comments</comments>
		<pubDate>Sat, 05 Nov 2011 18:19:24 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1225</guid>
		<description><![CDATA[This is the first attempt to integrate modules from the LIDA model into my current conception of the DM3 system. This is based on the interactive diagram of the LIDA architecture. The dotted line is a possible link between the dream model and the consolidation of episodic memory. It is still unclear what the &#8220;Attentional [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/first-attempt-to-integrate-lida-and-current-dm3-thinking/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Can a LIDA imagine its own behaviour?</title>
		<link>http://www.ekran.org/ben/wp/2011/can-a-lida-imagine-its-own-behaviour/</link>
		<comments>http://www.ekran.org/ben/wp/2011/can-a-lida-imagine-its-own-behaviour/#comments</comments>
		<pubDate>Sat, 05 Nov 2011 00:02:32 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1210</guid>
		<description><![CDATA[In attempting to think through a possible integration of LIDA and the current conception of the dreaming system, I&#8217;ve stumbled upon the above question. In the previous sketch, the content of memory (the current state of the &#8220;conceptual system&#8221;) is used to generate visual sensory data that is the dream content. In LIDA, it becomes [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/can-a-lida-imagine-its-own-behaviour/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Sketch of conceptual system before diving deeper into LIDA.</title>
		<link>http://www.ekran.org/ben/wp/2011/sketch-of-conceptual-system-before-diving-deeper-into-lida/</link>
		<comments>http://www.ekran.org/ben/wp/2011/sketch-of-conceptual-system-before-diving-deeper-into-lida/#comments</comments>
		<pubDate>Tue, 01 Nov 2011 23:39:06 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1194</guid>
		<description><![CDATA[In this post I will describe the conceptual subsystem, as I have imagined it up to this point, before looking more closely into the LIDA architecture. The central feature of this conception is that each high level feature, for example location in space, or colour (or redness), is considered independent. This contrasts with many systems [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/sketch-of-conceptual-system-before-diving-deeper-into-lida/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Next Steps, and Dreaming in Relation to Long-Term Memory.</title>
		<link>http://www.ekran.org/ben/wp/2011/next-steps-and-dreaming-in-relation-to-long-term-memory-2/</link>
		<comments>http://www.ekran.org/ben/wp/2011/next-steps-and-dreaming-in-relation-to-long-term-memory-2/#comments</comments>
		<pubDate>Mon, 31 Oct 2011 23:55:44 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1184</guid>
		<description><![CDATA[This is an excerpt from my email I wrote regarding next steps: 1. Make a diagram of the conception of the system as it was before, including how I was thinking of links between high level neurons having different weights for each high level feature (which may be made up of a vector of lower [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/next-steps-and-dreaming-in-relation-to-long-term-memory-2/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Biologically Inspired Cognitive Architectures</title>
		<link>http://www.ekran.org/ben/wp/2011/biologically-inspired-cognitive-architectures/</link>
		<comments>http://www.ekran.org/ben/wp/2011/biologically-inspired-cognitive-architectures/#comments</comments>
		<pubDate>Fri, 28 Oct 2011 19:42:21 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1160</guid>
		<description><![CDATA[On one hand we have the deep machine learning systems discussed in the previous post, which are quite complex (from a mathematical perspective) and only roughly informed by neuro and cognitive sciences. On the other hand are cognitive architectures that are inspired by biological knowledge (BICAs). These are systems that attempt to balance high level [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/biologically-inspired-cognitive-architectures/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Deep Machine Learning</title>
		<link>http://www.ekran.org/ben/wp/2011/deep-machine-learning/</link>
		<comments>http://www.ekran.org/ben/wp/2011/deep-machine-learning/#comments</comments>
		<pubDate>Fri, 28 Oct 2011 16:53:26 +0000</pubDate>
		<dc:creator>bbogart</dc:creator>
				<category><![CDATA[Dreaming Machine]]></category>
		<category><![CDATA[Production]]></category>

		<guid isPermaLink="false">http://www.ekran.org/ben/wp/?p=1147</guid>
		<description><![CDATA[As part of stepping back to see the big picture I&#8217;ve turned a second look at deep machine learning systems and biologically inspired cognitive architectures (as suggested by my supervisor), the latter of which will be discussed in another post. Deep machine learning systems attempt to resolve an issue with &#8220;shallow&#8221; learning which has increasingly [...]]]></description>
		<wfw:commentRss>http://www.ekran.org/ben/wp/2011/deep-machine-learning/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>

