“In Skyline’s systems, seeds for generating the diagram are sorted into various types of agents following certain behaviors and appearance transformations. They are driven by either the song’s audio spectrum with different customized layouts, or animated sequence of the vocalist, collectively forming a complex and organic outcome.”
Making the video was eye-opening and brain-opening. It introduced us to concepts we’d never heard of – like machine learning and artificial neural networks – and ever since, we’ve been kind of fascinated by them. Machine learning, in particular, is a very active area of Computer Science research, with far-ranging applications beyond voice search – like machine translation, image recognition and description, and Google Voice transcription.
So… still curious to know more (and having just started this project) we found Google researchers Greg Corrado and Christopher Olahand ambushed them with our machine learning questions.
Ethel The Notebook is getting very full. It might time for retirement soon.
It’s been a beautiful weekend, like the summer’s not ready to let go, I’ve been outside, mostly, hacking at the hedges. Pleasant but very tiring.
Within the space of a week UK politics has changed completely which is a breath of fresh air whether you agree with the direction or not. You can tell how much it has changed by the level of hysterical outrage in the old school press. It can be difficult to take your eyes off the news. Fun times.
If your not watching This Is England ’90, do yourself a favour and get with it. When it’s done, it’s done.
Twitter and Instagram users can learn a lot from a 1920s journalist – Paul Mason/A Graphic Account of Roxane Gay and Erica Jong’s Uncomfortable Conversation by Mari Naomi/Meet the Artist Making GIFs to Ridicule All the Shit Women Deal With: Isabel Chiara/The Tsarnaev trial: Drawing a line/Hunter S Thompson on Now, from the Past/Jeremy Corbyn’s new PMQs has Tory MPs turning to tranquil pursuits like sketching MPs/’Ukraine’s Banksy’ on his time imprisoned by separatist rebels – in pictures/Megan Nicole Dong – “I’ve been doing a series of comics about men being deceived by makeup.”/Judy Pfaff/
At BDH I was part of the team that worked on The Countdown To Life, a three part series produced by BBC Science in association with the Open University, exploring some of the latest research into understanding of human development, from conception to birth. With a complex pipeline, an imaginative and groundbreaking approach and with an array of the latest technology and software, the BDH team produced hundreds of shots of spell binding imagery illustrating the remarkable transformations that take place during those early stages.
Episode One transmits tonight (Monday 4th September 2015) on BBC2 and will subsequently be available on the iPlayer.
Why does anyone share anything ever. Does it help people? These are all thoughts and findings and I collected them over time and then here they are. What I thought was worth passing on. Perhaps I should be weaving it into some kind of artful enterprise, but for the moment there is only this. A list. I’m work on making more stuff, but there is very little time, it’s not easy. I’m posting “daily” sketches at Instagram, so follow me there if you like.
I have to say I have been haunted by thesetwo renderings from real time tech leonardo, Kyle McDonald. When I was little I remember imagining animation as it might be if each frame was as detailed as an oil painting, it didn’t take much practical experience for me to realise that such ideas would lead to certain doom of endless work, no friends and little result.
Bring on neural network analysis, the Inception Network and Google’s Deep Dream. This from the Bethge Lab.
In fine art, especially painting, humans have mastered the skill to create unique visual experiences through composing a complex interplay between the content and style of an image. Thus far the algorithmic basis of this process is unknown and there exists no artificial system with similar capabilities. However, in other key areas of visual perception such as object and face recognition near-human performance was recently demonstrated by a class of biologically inspired vision models called Deep Neural Networks. Here we introduce an artificial system based on a Deep Neural Network that creates artistic images of high perceptual quality. The system uses neural representations to separate and recombine content and style of arbitrary images, providing a neural algorithm for the creation of artistic images. Moreover, in light of the striking similarities between performance-optimised artificial neural networks and biological vision, our work offers a path forward to an algorithmic understanding of how humans create and perceive artistic imagery.
and the algorithm, the dream doings that wre blowing people away a month or so ago there are people around the word making this mad math work on images like this, and as you can read here, it’s not at After Effects plug-in utility level yet (there appears to be many lvels of adjustment and feedback loops), but i’m sure it’s only a matter of time and several levels of genius away.
“While working, I suddenly heard a noise and looked up to find Robert Hughes, the art critic of Time magazine, staring at me in disbelief. ‘But you’re Philip Glass! What are you doing here?’ It was obvious that I was installing his dishwasher and I told him I would soon be finished. ‘But you are an artist,’ he protested. I explained that I was an artist but that I was sometimes a plumber as well and that he should go away and let me finish.”
“”We abide by cultural directives that urge us: clarify each thought, each experience, so you can cull from them their single dominant meaning and, in the process, become a responsible adult who knows what he or she thinks.
“But what I try to show is the opposite: how at every moment, the world presents us with a composition in which a multitude of meanings and realities are available, and you are able to swim, lucid and self-contained, in that turbulent sea of multiplicity.”
Richard Foreman
*
Collaborative Self-Contained-Self-Portrait in That Sea of Multiplicity
Paul Greer 