The node performers made their first public apparence at the Digital Futures organised by V&A for the Eva conference in London. Equiped with headphones, their visitors listen to their generative poetry. Very warm welcome for them in their little cinema cardboard box.
Prototyping Char RNN Neural networks generating text
Trying to find a voice for the crafted electronic nodes- Node Poetry
In the process of characteristation, the nodes need a voice . I like the idea of the nodes generating their own poetry based on texts I will fed to them. The challenge then , is to find appropriate texts to train the neural network
testing a Char RNN model based on Max Woolf ‘s training model : https://github.com/minimaxir/textgenrnn, an open-source framework by Max Woolf, written in Python and powered by Tensorflow.
First set of seeding texts were user guide for tourist and servo safety guide ,
“Keep quiet when you are punctual if taking part in a shop
loosen up and bring an adventurous spirit
take time to a complete stop
applicable regulations will result in death or serious
Install and avoid hazards involved are authorized to work on your knife.
loosen up and bring an adventurous spirit
Install and all other people’s belongings with the fork parallel across the right side of your host
Ensure you are punctual if taking part in a shop
It is advisable to take your place in the right while eating.”\
The result is fun but not any relations with the idea of the network of nodes.
Better result with another set of texts : Wendy Chun and Updating to remain the same. Cambridge, Massachusetts : The MIT Press, 2016 and U.A Meijas . Off the Network. USA: Electronic Mediations , University of Minnesota Press, 2013, in addition to extract from my essay on network masks and some further thoughts about puppetry.
Put the mask on your face, and become a node’, ‘between 0 and 1
This is the marionette
the Network is Blind
Internet is Myopic
the puppet is Workaholic
the Network is a Trail
the interface is Sniffing
the interface is a Collective Traveller
sensor is on
sensor is off
the code is binary
shadows are invisible
we are the machines
Ask the marionette
a puppet never dies
we are humans…
asking the model to qualify the main social media : ” google computers are invisible, google the mask on your face, and become a node “
taking the “good sentences ” produced by the model and put it again in the training model
Chatbot Personality by 5agado
Tom Bocklish : https://towardsdatascience.com/personality-for-your-chatbot-with-recurrent-neural-networks-2038f7f34636
D.Shiffmann : https://www.youtube.com/watch?v=slmSCEho31g&list=PLRqwX-V7Uu6aDUo_ia-Vq2UZZGaxJ9nRo
Using RiverScript https://www.rivescript.com/
Text to Speech p5 js : https://www.youtube.com/watch?v=v0CHV33wDsI
Speech to Text p5 js https://www.youtube.com/watch?v=q_bXBcmfTJM
Riverscript to process the input text to output text https://www.rivescript.com/
Text Generator, All about Chatbot
Markov Chain with D.Shifman https://www.youtube.com/watch?v=v4kL0OHuxXs
App Recommanded by Janelle Shanne:
1. textgen-rnn – an open-source framework by Max Woolf, written in Python and powered by Tensorflow. It’s the easiest to install (though you still have to know your way around command line a bit) and comes pre-trained so you can get interesting results even from tiny datasets. It runs fine on an ordinary computer’s CPU, and lets you train the same network successively on different datasets, which is fun. It’s not as powerful as the other frameworks, but just fine for simple lists of names. (tested 15th may )
2. tensorflow char-rnn – an open-source framework by Chen Liang, written in Python. It has tons of flexibility, including the ability to adjust dropout, save frequency, and number of saved snapshots during training, and the ability to adjust temperature during sampling. There’s a tutorial here for running it on AWS, and I’m hoping to find a good tutorial for Google Cloud as well.
3. Andrej Karpathy’s char-rnn, an open-source neural network framework for torch (written in Lua). This one has great flexibility in training/sampling parameters, and it seems to run faster on my 2010 Macbook Pro’s CPU than the python/tensorflow models. I’ve been using this one for the simpler datasets.
Ross Goldwin General Method
- prepend the seed with a pre-seed (another paragraph of text) to push the LSTM into a desired state.
- Use high quality sample of output from the model you’re seeding with length approximately equal to the sequence length (see above) you set during training.
- Seed the LSTM with a meaningful text, that the machine would complete
- build a data set , corpus
- Choosing the right settings for a given corpus
- train the model
- generate output
- train again
James Loy : How to build your own Neural Network from scratch in Python- A beginner’s guide to understanding the inner workings of Deep Learning
Chatbot Personality by 5agado , github
Sit down comfortably with your eyes closed. Try to imagine a scene that catches your topic/theme in a nutshell; you can try to imagine that your topic/ theme is being presented as a film or theatre play and construct a scene that presents crucial aspects of it.
Or you can try to think of a scene as part of a personal memory where you felt that crucial issues concerning your topic were at stake. Remember that even a purely theoretical topic/theme can be articulated in a scene. Try to mobilize all your senses when you imagine the scene. If possible, let your mind flow back to the work you did with the touching hands.
proposed by Helen Pritchard based on Nina Lykke. Writing Academic Texts Differently: Intersectional Feminist Methodologies and the Playful Art of Writing (Routledge Advances in Feminist Studies and Intersectionality) (p. 155). Taylor and Francis. Kindle Edition.
-Behind the screen, we, the components, are talking, quietly so quietly that you could hardly hear us. Actually , we are constantly chatting , bubbling : “01101000 01100101 01101100 01101100 01101111 00100000 01110111 01101111 01110010 01101100 01100100 00100000 00100001” chanting “HOHA DADO BIDABI KOKA BIDEKA!” . We are so busy, sorting out your data: receive, store, delete, update, send. Little busy shadows, enchained together with no choice but to communicate and release the data we are taking from you. Behind the screen, there is a 24 hours show, a constant ballet of binaries , an infinite concerto of 0 and 1, sadly no one can hear us, except perhaps your EMF detector.
Suddenly a red light is activated, someone is looking at the screen, someone is typing on the keyboard or maybe it is a sound or a touch? Who or what is this? I have a unique task, I know what to do …hey! this is my input! Let’s go and give it a byte! Iterate, map, reiterate, variables, vectors, int, float, strings loop and loop again and return the arrays to my algorithmic friend!
At the speed of an electron, we are sending feedback not only to you, the one with the keyboard, but also to our hosts: the cookies, in a protocol, a language , that no human could speak fluently. Luckily, we know how to speak human. And thanks to the continuous improvement of the human computer interfaces : you, the users are by now, perfectly trained to give us the correct input.
But with humans, there is always an end . You are now releasing the keyboard and leaving the computer. Behind the screen, and until the next time we will meet, there is a new show going on , a new story we tell to each other through the wires or in the clouds, this is is a story based on the memory of our encounter with you. So come back , do not type on the keyboard, do not look at the screen, try to listen to the story, because it is not only about you * but also about us.
* Chun,W. 2016, Updating to remain the same,MIT Press.
“Write a list of false starts or dead ends you have encountered. If you cannot quite place them in your mind, try going to places that are relevant or integral to your research.
Go back to moments in time in particular places where something happened that made you feel you were utterly stuck. You can do this either by physically going to that place and observing yourself or by going there through your memories. Read out your list to others in the group and discuss. Choose one example and write your own story about a difficult moment in your research. Describe the situation: When did it happen, where were you, what were you supposed to do, what did you do? Be concrete: pay attention to perceptions, senses, sounds, smells, colours. Take note of incidental, seemingly insignificant details and things; switch off your cognitive response. “
exercice proposed by Helen Pritchard
False starts and dead ends :
I wanted to explore virtual reality as I was curious of the way bodies are moving when users wear their virtual headset and the relation between the body left outside and the virtual bodies. I realised that I would not have had enough physical material for me to craft within only few months of exploration. Furthermore, my first readings and the readings proposed by Helen Pritchard have led me to embrace the broader subject of our entangled life within the digital networks and their artifacts, the internet of things.
the 5% Skeleton Project or how to stop being creative to save the date:
Submerged by the material and by the tensions of the academic system, I feel stretched like a knitted sensor. Asking me to switch off my cognitive response is like asking electron to stop leaving the ground to the power source. If it would be a smell it would be bitter or a colour it would be dark blue and there will be no sound. Motors without purpose and knitted wires are waiting to find their places in a network installation. The poetic space is not heard, and have not found its place in the system. Self preservation would tell to not bother, but how oblivious could I be without leaving the system?
Feeling comfort when returning to the material and confident that I will find a way to express what is needed, to answer the “artistic call” if I have more time to explore. How to deal with different agenda between the internal and external urgency to deliver? I am looking for the conductive threads and the connections to the micro controller, buying time and trying to transmute the external deadlines into input for my creative process.
“Turn to the person next to you. Both of you raise your arms so that your hands are at chest level. Spread your fingers and gently place your fingertips against your neighbours’ fingertips.
Then close your eyes. Hold this pose for 1.5 minutes. At the end of the 1.5 minutes open your eyes. Look into the eyes of your partner for a short time (about 10 seconds). (Don’t do either of these actions for much longer than the time I suggest; otherwise, thoughts intrude and the bodily awareness is dispersed. Thoughts will, of course, intrude during the 1.5 minutes, but the body awareness remains fresh.)” exercice proposed by Helen Pritchard based on Nina Lykke. Writing Academic Texts Differently: Intersectional Feminist Methodologies and the Playful Art of Writing (Routledge Advances in Feminist Studies and Intersectionality) (p. 67). Taylor and Francis. Kindle Edition.
Closing my eyes, raising my hands. So lonely, in the shadows of their thoughts, so lost in the silence of their breathes. My arms reaching for the others, alone but also taller, extended. Push and feel their resistance. Being pushed and resist, to keep or not to keep contact. Need to release the tensions, are there mine or someone else? Finding my breath again and the borders of my skin. My body is entangled, my dreams are not yours. They pull me out. I have to leave. Ciao.
Things about entanglement , unmasking the networks and turn the nodes into paranodes.
Mejias suggestions for playing the networks in order to disrupt them which is to reveal what is invisible. Looking at how the networks could have their own experience of themselves, computer can be a source for “producing , for example, the unknown out of the known” .
Overall, I want to reflect a space where humans and machines are intertwined and where hierarchy is always under review.
Always on the back of my head, how to illustrate our entanglement with the network and the internet of things Everything is merged , but everyone has his own character
I wanted to treat the human as equal as the automata
The nodes are having fun together without us
when they sense our presence they communicate in their own language, audiovisual
their extended bodies are entangled with ours
showing the roots, processing without thinking about how to show the process, then reverse engineering to explain the process
combination of organic artefacts made of electronics and traditional basketry and puppet making
In term of inspiration, I am looking at Rebecca Horn and her machines with souls, Calder and Tinguely for their kinetic installations, to Bruno Munari and his Movimento Arte Concreta, the Italian movement for concrete art and more recently at Christian Boltanski for his shadow sculptures.
and also reading Simanowski, R. 2011, Digital Art and Meaning Reading Kinetic Poetry, Text Machines, Mapping Art, and Interactive Installations and Slater, C 2015, MIT Press Alien Agency Experimental Encounters with Art in the Making
I am also inspired by the creative process as exposed in Compelling Image: Mask Improvisation for Actor Training and Performance Paperback – 31 Oct 1996 by