Text reproduction with machine learning - Revision history

Karl: Text replacement - "{{#ev:youtube\|(.*)}}" to " "

2024-01-30T07:39:05Z

Text replacement - "{{#ev:youtube\|(.*)}}" to "<htmltag tagname="iframe" width="1080" height="720" frameborder="no" src="https://www.youtube.com/embed/$1"></htmltag> "

← Older revision		Revision as of 09:39, 30 January 2024
Line 238:		Line 238:
	Theory on [https://karpathy.github.io/2015/05/21/rnn-effectiveness/ recurrent neural networks]		Theory on [https://karpathy.github.io/2015/05/21/rnn-effectiveness/ recurrent neural networks]
	Video introduction to recurrent neural networks:		Video introduction to recurrent neural networks:
	~~{{#ev~~:youtube\|WCUNPb-5EYI}}		<htmltag tagname="iframe" width="1080" height="720" frameborder="no" src="https://www.youtube.com/embed/WCUNPb-5EYI"></htmltag>


	=Some excerpts from generated texts:=		=Some excerpts from generated texts:=
Line 299:		Line 300:


	~~{{#ev~~:youtube\|5aD-H7Pqg9s}}		<htmltag tagname="iframe" width="1080" height="720" frameborder="no" src="https://www.youtube.com/embed/5aD-H7Pqg9s"></htmltag>

Juliette at 15:17, 27 August 2018

2018-08-27T15:17:50Z

← Older revision		Revision as of 17:17, 27 August 2018
Line 22:		Line 22:
	* To have Python 3.6 installed (1)		* To have Python 3.6 installed (1)
	* We used Tensorflow, so if you’re cool with Python, you could install it on forehand, otherwise we did it during the workshop or in advance.		* We used Tensorflow, so if you’re cool with Python, you could install it on forehand, otherwise we did it during the workshop or in advance.
	* Text material that you wanted to feed the machine with. This could be text that you had written yourself or found somewhere. Short text passages were internalized by the machine very quickly. Some brought excerpts, a few pages or a book. The texts were remix, reproduce and produce more of. Some texts that were used: The Communist Mannifesto by Karl Marx, ~~the scripts from all~~ Harry Potter ~~movies~~, The Cyborg Manifesto from Donna Haraway, some newspapers headlines. We needed the text in .txt files, but you can use formats like Markdown or XML like syntax to define headlines, paragraphs, bullet points, quotes. You can format the text however you like, as long as it's in one or many .txt files.		* Text material that you wanted to feed the machine with. This could be text that you had written yourself or found somewhere. Short text passages were internalized by the machine very quickly. Some brought excerpts, a few pages or a book. The texts were remix, reproduce and produce more of. Some texts that were used: The Communist Mannifesto by Karl Marx, Harry Potter books, The Cyborg Manifesto from Donna Haraway, some newspapers headlines, Aaron Schwartz's blog... We needed the text in .txt files, but you can use formats like Markdown or XML like syntax to define headlines, paragraphs, bullet points, quotes. You can format the text however you like, as long as it's in one or many .txt files.

	(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3.		(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3.
Line 276:		Line 276:

	==Neural Donna==		==Neural Donna==

			[[File:Donnalearning.gif\|thumb]]

	"This is a common longuage, like any other time, we are not innocence is a suptoid tritical aptrociated by machines, and thinging a new developmental competition is a network and ethnography, and their intimate, uncture, and monstrous is a major form of contention.		"This is a common longuage, like any other time, we are not innocence is a suptoid tritical aptrociated by machines, and thinging a new developmental competition is a network and ethnography, and their intimate, uncture, and monstrous is a major form of contention.
	But these each of the social relations on science and technology proveses; which we have alsocindicated in the social relations of science and technology provide fresh moniters the mochice of the most primitive, and its competent, potent sistems, cultural revolutionary subjects might be anoun the definition of the self, the intersise from without realistically intersived in the face feainist sensitivity, a dimage of the oppositional intorsection of feminism account be a view of papsidely is notestate."		But these each of the social relations on science and technology proveses; which we have alsocindicated in the social relations of science and technology provide fresh moniters the mochice of the most primitive, and its competent, potent sistems, cultural revolutionary subjects might be anoun the definition of the self, the intersise from without realistically intersived in the face feainist sensitivity, a dimage of the oppositional intorsection of feminism account be a view of papsidely is notestate."

	==The Correspondent headlines==		==The Correspondent headlines:==

	"This is the voice of the safety syndrome		"This is the voice of the safety syndrome
Line 292:		Line 294:
	The problem (and 9 more stories to catch up to)		The problem (and 9 more stories to catch up to)
	An ode to Jonistori"		An ode to Jonistori"

			==Neural Queering the Map:==
			[[File:Qtmbot2.jpg\|thumb]]


	{{#ev:youtube\|5aD-H7Pqg9s}}		{{#ev:youtube\|5aD-H7Pqg9s}}

Juliette at 15:10, 27 August 2018

2018-08-27T15:10:22Z

← Older revision		Revision as of 17:10, 27 August 2018
Line 26:		Line 26:
	(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3.		(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3.

			<gallery>
			Moritz5.jpg
			Moritz2.jpg
			Moritz3.jpg
			Moritz1.jpg
			Moritz4.jpg
			</gallery>

	=Basic preparation=		=Basic preparation=

Juliette at 14:59, 27 August 2018

2018-08-27T14:59:22Z

← Older revision		Revision as of 16:59, 27 August 2018
Line 9:		Line 9:
	\|Print=No		\|Print=No
	}}		}}
			[[File:HSDA18-Workshop-Moritz Ebeling.png\|thumb]]

	In the era of data, intelligence and computing, the authenticity of any digital content is not longer guaranteed. With machine learning technology, a human voice can be imitated, a moving image can be manipulated in real time, texts can be phrased by using raw data. All to make up something „real“. To get a glimpse of what’s going on, we built our own deep learning network!		In the era of data, intelligence and computing, the authenticity of any digital content is not longer guaranteed. With machine learning technology, a human voice can be imitated, a moving image can be manipulated in real time, texts can be phrased by using raw data. All to make up something „real“. To get a glimpse of what’s going on, we built our own deep learning network!
	In this workshop, we trained a given neural network on original text to reproduce it, remixed it, produced more of it. Sometimes the output was complete rubbish, sometimes the algorithm repeated passgages from the original. But certainly it invented or rehashed content based on the given input, so who is faking whom?		In this workshop, we trained a given neural network on original text to reproduce it, remixed it, produced more of it. Sometimes the output was complete rubbish, sometimes the algorithm repeated passgages from the original. But certainly it invented or rehashed content based on the given input, so who is faking whom?
Line 284:		Line 286:
	An ode to Jonistori"		An ode to Jonistori"

	~~[[File~~:~~HSDA18~~-~~Workshop-Moritz Ebeling.png\|thumb]]~~
			{{#ev:youtube\|5aD-H7Pqg9s}}

Juliette at 14:57, 27 August 2018

2018-08-27T14:57:02Z

Show changes

Juliette at 14:48, 27 August 2018

2018-08-27T14:48:13Z

@@ Line 157: / Line 157: @@
 * The program will first ask you to type in the name of your current project folder. After that, it will ask you wether you want to train or play the model.
-[[File:Training-start.png]]
+[[File:Training-start.png|thumb]]
 * Training
@@ Line 214: / Line 214: @@
+}
-:45 What is happening?
+'''What is happening?'''
-:15 Discussion: What can we do with that?
+[[File:NetworkMoritz.jpg|thumb]]
-:00 Lunch, while the computers are working
+* Recurrent neural networks
-:00 Play and analyse the results
-:30 Free experiments, work, discussions, help, questions
+'''Other resources'''
-:00 Prepare and share your results
+Theory on [https://karpathy.github.io/2015/05/21/rnn-effectiveness/ recurrent neural networks]
-:00 Presentation
+'''Some excerpts from generated texts:'''
 [[File:HSDA18-Workshop-Moritz Ebeling.png|thumb]]

Juliette at 14:41, 27 August 2018

2018-08-27T14:41:37Z

Show changes

Juliette at 14:12, 27 August 2018

2018-08-27T14:12:52Z

← Older revision		Revision as of 16:12, 27 August 2018
Line 9:		Line 9:
	\|Print=No		\|Print=No
	}}		}}
	In the era of data, intelligence and computing, the authenticity of any digital content is not longer guaranteed. With machine learning technology, a human voice can be imitated, an moving image can be manipulated in real time, texts can be phrased by using raw data. All to make up something „real“. To get a glimpse of what’s going on, ~~let’s build~~ our own deep learning network!		In the era of data, intelligence and computing, the authenticity of any digital content is not longer guaranteed. With machine learning technology, a human voice can be imitated, a moving image can be manipulated in real time, texts can be phrased by using raw data. All to make up something „real“. To get a glimpse of what’s going on, we built our own deep learning network!
	In this workshop, we ~~will train~~ a given neural network on original text to reproduce it, ~~remix~~ it, ~~produce~~ more of it. Sometimes the output ~~will be~~ complete rubbish, sometimes the algorithm ~~will repeat~~ passgages from the original. But certainly it ~~will invent~~ or ~~rehash~~ content based on the given input, so who is faking whom? ~~This workshop can be fun for beginners and pros.~~		In this workshop, we trained a given neural network on original text to reproduce it, remixed it, produced more of it. Sometimes the output was complete rubbish, sometimes the algorithm repeated passgages from the original. But certainly it invented or rehashed content based on the given input, so who is faking whom?

	'''~~Please bring~~'''		This workshop was fun for beginners and pros!


			'''For this workshop we needed:'''
	* A computer + power plug		* A computer + power plug
	* ~~Know~~ where to find your computer’s Terminal or Console		* To know where to find your computer’s Terminal or Console
	* ~~Have~~ Python 3 installed (1)		* To have Python 3.6 installed (1)
	* We ~~will use~~ Tensorflow, so if you’re cool with Python, you ~~can~~ install it ~~already~~, otherwise we do it during the workshop or in advance.		* We used Tensorflow, so if you’re cool with Python, you could install it on forehand, otherwise we did it during the workshop or in advance.
	* Text material that you ~~want~~ to feed the machine with. This ~~can~~ be text that you ~~wrote~~ yourself or found somewhere. Short text passages ~~will be~~ internalized by the machine very quickly~~, so this can be a good experiment but might not be that interesting to fill a whole day~~. ~~So bring more text~~, a few pages or a book~~, or even more~~. ~~Think of text that you want to~~ remix, reproduce and produce more of. ~~E.g. all surrealist poems from Pablo Neruda,~~ The Communist Mannifesto by Karl Marx, the scripts from all Harry Potter movies, ~~Newspaper headlines~~ from ~~the last year~~, ~~whatever~~. We ~~will need~~ the text in .txt files, but you can use formats like Markdown or XML like syntax to define headlines, paragraphs, bullet points, quotes. You can format the text ~~whatever~~ you like, as long as ~~its~~ in one or many .txt files.		* Text material that you wanted to feed the machine with. This could be text that you had written yourself or found somewhere. Short text passages were internalized by the machine very quickly. Some brought excerpts, a few pages or a book. The texts were remix, reproduce and produce more of. Some texts that were used: The Communist Mannifesto by Karl Marx, the scripts from all Harry Potter movies, The Cyborg Manifesto from Donna Haraway, some newspapers headlines. We needed the text in .txt files, but you can use formats like Markdown or XML like syntax to define headlines, paragraphs, bullet points, quotes. You can format the text however you like, as long as it's in one or many .txt files.

			(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3.


	(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3. If you don’t know what that means, ask me or others in the days prior to the workshop.

	[[File:HSDA18-Workshop-Moritz Ebeling.png\|thumb]]		[[File:HSDA18-Workshop-Moritz Ebeling.png\|thumb]]

Juliette at 15:57, 10 August 2018

2018-08-10T15:57:26Z

← Older revision		Revision as of 17:57, 10 August 2018
Line 21:		Line 21:
	(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3. If you don’t know what that means, ask me or others in the days prior to the workshop.		(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3. If you don’t know what that means, ask me or others in the days prior to the workshop.

	[[File:Moritz.~~jpg~~\|thumb]]		[[File:HSDA18-Workshop-Moritz Ebeling.png\|thumb]]

Juliette at 20:03, 17 July 2018

2018-07-17T20:03:09Z

← Older revision		Revision as of 22:03, 17 July 2018
Line 13:		Line 13:

	'''Please bring'''		'''Please bring'''
	– A computer + power plug		* A computer + power plug
	– Know where to find your computer’s Terminal or Console		* Know where to find your computer’s Terminal or Console
	– Have Python 3 installed (1)		* Have Python 3 installed (1)
	– We will use Tensorflow, so if you’re cool with Python, you can install it already, otherwise we do it during the workshop or in advance.		* We will use Tensorflow, so if you’re cool with Python, you can install it already, otherwise we do it during the workshop or in advance.
	– Text material that you want to feed the machine with. This can be text that you wrote yourself or found somewhere. Short text passages will be internalized by the machine very quickly, so this can be a good experiment but might not be that interesting to fill a whole day. So bring more text, a few pages or a book, or even more. Think of text that you want to remix, reproduce and produce more of. E.g. all surrealist poems from Pablo Neruda, The Communist Mannifesto by Karl Marx, the scripts from all Harry Potter movies, Newspaper headlines from the last year, whatever. We will need the text in .txt files, but you can use formats like Markdown or XML like syntax to define headlines, paragraphs, bullet points, quotes. You can format the text whatever you like, as long as its in one or many .txt files.		* Text material that you want to feed the machine with. This can be text that you wrote yourself or found somewhere. Short text passages will be internalized by the machine very quickly, so this can be a good experiment but might not be that interesting to fill a whole day. So bring more text, a few pages or a book, or even more. Think of text that you want to remix, reproduce and produce more of. E.g. all surrealist poems from Pablo Neruda, The Communist Mannifesto by Karl Marx, the scripts from all Harry Potter movies, Newspaper headlines from the last year, whatever. We will need the text in .txt files, but you can use formats like Markdown or XML like syntax to define headlines, paragraphs, bullet points, quotes. You can format the text whatever you like, as long as its in one or many .txt files.

	(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3. If you don’t know what that means, ask me or others in the days prior to the workshop.		(1) For beginners, this is a quite heavy task to either find out which version you have installed or to update to version 3. If you don’t know what that means, ask me or others in the days prior to the workshop.

	[[File:Moritz.jpg\|thumb]]		[[File:Moritz.jpg\|thumb]]