neural networks

By studying the connections between neurons, we can find meaningful algorithms in the weights of neural networks.
TPG
2020-07
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models Research paper:  https://arxiv.org/pdf/2003.03808.pdf Tester:  …
Lacework is a new work by Everest Pipkin that uses artificial neural networks to reinscribe the videos of MIT’s Moments in Time Dataset.
Transmediale 2020 End to End Exchange #5  Panel discussion Neural Network Cultures  with Tega Brain, Stephanie Dick, Katharine Jarmul, Fabian Offert and Matteo Pasquinelli
A paper submitted to this year’s International Conference on Learning Representations (ICLR) may explain why. Researchers from the University of Tübingen in Germany found that CNNs trained on …
The face of your voice 3D, from the verbal to the physiognomic Contemporary life seems to be an endless game of data quantification, moving across different cultural domains. The former is an …
Early Modern Computer Vision - Leonardo Impett https://docs.google.com/document/d/1LKs82uKkSgQ-4wGUQ4Dwzxgnerx2e6zbHf4iGIHuJmI/edit#heading=h.60chgdizcy6h
Reconstructing 3D human shape and pose from a monocular image Reconstructing 3D human shape and pose from a monocular image is challenging despite the promising results achieved by the most recent …
TPG
2019-09
DeepPrivacy A fully automatic anonymization technique for images. This repository contains the source code for the paper “DeepPrivacy: A Generative Adversarial Network for Face …
Strike (with) a Pose: Neural networks are easily fooled by strange poses of familiar objects Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize …
We introduce natural adversarial examples – real-world, unmodified, and naturally occurring examples that cause classifier accuracy to significantly degrade. We curate 7,500 natural adversarial …
While humans pay attention to the shapes of pictured objects, deep learning computer vision algorithms routinely latch on to the objects’ textures instead Image: Robert Geirhos …
Colorful Image Colorization Richard Zhang, Phillip Isola, Alexei A. Efros, 2016 Given  a  grayscale  photograph  as  input,  this  paper  attacks the problem of hallucinating a plausible colour …
Mushy from Everest Pipkin is a free asset pack of 824 neural network-generated isometric tiles residing in the creative commons. The sets ave been trained on; plants, building materials, flooring, …
Mike Tyka, Dreams of Imaginary People, 2017 (constantly morphing hypnotic GAN portraits) http://www.miketyka.com/projects/dreams/
mario-klingemann: ChainGAN portrait series by Mario Klingemann
prostheticknowledge: Computed Curation Project by Philipp Schmitt creates a book of photography curated and annotated using Machine Learning: Computed Curation is a photobook created by a computer. …
notes from Katriona Beales talk at the Creative AI meetup at The Photographers' Gallery.
prostheticknowledge: Realtime Neuratorial Art Artist Memo Atken has been exploring methods to generate neural network images in realtime. It started with his #Learningtosee project, with a ‘blank’ …
Miša Skalskis is a Lithuanian artist, currently based in The Hague and Vilnius. His recent work revolves around exploration of vision without image and hearing without sound. Skalskis explores …
we can ask a second neural net to determine whether the output of a first looks real or fake. This technique is called adversarial learning. It’s often compared to the relationship between someone …
by Trevor Paglen “The more images Facebook and Google’s AI systems ingest, the more accurate they become, and the more influence they have on everyday life. The trillions of images we’ve been trained …
We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting. To perform this mapping, we …
‘Topological Visualisation of a Convolutional Neural Network’  by Terence Broad The aim of this project was to apply some of the techniques used to data visualisation techniques used to visualise …
TPG
2016-11
prostheticknowledge: AI Experiments Yesterday, Google released a load of creative coding experiments using artificial intelligence and neural networks to demonstrate how the technology can be …
TPG
2016-10
Decision Space by Sebastian Schmieg Decision Space by Berlin-based artist @sebastianschmieg takes a closer look at how machine vision datasets are created: developed on the website of The …
Scientists at Google and elsewhere are turning to the 30-year-old digital music standard MIDI to teach neural networks how to write music.
algopop: Maria Callas - Style Transfer by Lulu xXX Paris-based CGI artist Lulu xXX has been experimenting with style transfer, and has made one of the more beautiful videos I’ve seen using this …
Using deep learning to generate faces - https://github.com/zo7/facegen We can specify random “illegal” parameters to generate interesting images.
TPG
2016-09
prostheticknowledge: UberNet Computer Vision research from Iasonas Kokkinos demonstrates method neural networks can assist in the field, encompassing various methods into one system: In this work we …
prostheticknowledge: Generating Videos with Scene Dynamics Proof of concept computer science research from Carl Vondrick, Hamed Pirsiavash and Antonio Torralba can generate video content from a …
New detection technologies will move us toward a more precise understanding of images.