Submit a Project

ML x ART

A showcase with creative machine learning experiments

👋 I'm Emil, a resident at the Google Arts & Culture Lab. I've curated this collection.

Year
Artist
Technology
Theme
Medium
Default order

Daniël Korssen

Create a shared playlist on Spotify and create a digital dance party by animating each dancer with PoseNet

PoseNet

Memo Akten

Pick random words from Word2Vec and look at their relationships to the words ‘man’ and ‘woman’

Word2Vec

Jason Salavon

Visualize the entire ImageNet dataset in vertical rows

ImageNet

Jeff Thompson

Generative touch with a robotic arm, translating image features to movements

Hardware, CNN, RNN

YACHT, Ross Goodwin, Tom White, Mario Klingemann

An album with songs generated with Magenta’s MusicVAE model and lyrics made by an LSTM trained by Ross Goodwin

Magenta, VAE, NSynth Super

Olga Vechtomova

Generate lyrics with an VAE trained with seven different styles

VAE

Google Creative Lab

Collect dataset and use AutoML to classify the images

AutoML, CNN, Hardware

Dani Joy

Produce large scale Style Transfer-like artworks, print, and paint over

Style Transfer

Holly Grimm

Use CycleGAN to translate street images to artworks from WikiArt

GAN, CycleGAN

Tom White

Pairing New Yorker front-pages by measuring the distance from features extracted from a CNN

CNN, NNS

Gene Kogan

Continuously zoom in a image and apply DeepDream and use Dense Captioning to label objects in the video

DenseCap, DeepDream

Mike Tyka

A GAN trained on faces from Flickr

GAN

Alexander Mordvintsev

Run an image through a pre-trained CNN, and then upscale the image backward. For each layer, adjust the image according to the difference between the activations and the image

CNN, Activations, DeepDream, Gradient Ascent

Parag K. Mital

Corpus-based visual synthesis recreating the Simpsons intro with the intro from the Family Guy

Corpus-based synthesis

Bruce MacDonald

Fooling Facial Detection with Fashion

Facial Detection

Ivan Pravdin

StyleGAN blended model from human poses GAN and FFHQ

StyleGAN, GAN

Diego Porres

GAN-generated Mexican and Guatemalan textiles

DCGAN, GAN

Xinyue Yang

Classify voice with an RNN and match it with doodles

RNN, Classification, QuickDraw

Jonathan Fly

Apply GauGAN on Charlie Chaplin dressed as a tree

GauGAN, GAN

Ziv Epstein, Matt Groh, Manuel Cebrian, Iyad Rahwan

Use GAN inpaintings to add spirits to videos

GAN, Inpainting

OpenAI

Create images from text captions using GPT-3 and trained on 400M text–image pairs

DALL·E, GPT

Aarati Akkapeddi

Visualizing face-recognition data

Face recognition

Dani Joy

An overpainted GAN interpolation of a smoking monkey

GAN

Ryan Murdock

Maximize the perceptual difference between each image and minimize the difference between the outputs and images from a dataset

Min-Max

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners