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

Anna Ridler, Ben Heim

Organise personal art collection with t-SNE, compose music according to each clusters, and detect each clusters with a camera to play corresponding music

t-SNE, CNN, Classification, Camera, Device

Jonas Jongejan, Henry Rowley, Takashi Kawashima, Jongmin Kim, Nick Fox-Gieg, Google Creative Lab

A user is challenged to draw an object and a CNN model tells if you are correct

CNN, Classification

Golan Levin, Lingdong Huang

A collection of “ambigrammatic” images, generated with a GAN, legible as faces in both upside-down and right-side up orientations

GAN, StyleGAN2, Super-resolution

Zhihao Ouyang, Yihang Yin, Kun Yan, Jian Wu, Xiaolin Hu

Compose violin music with prompts trained with a combination of a CNN and RNN, and performed

RNN, CNN, rGMIR, Magenta

David Ha, Jürgen Schmidhuber

A neural net-generated environment where reinforcement learning agents learn

Reinforcement Learning, Mixture Density Networks, RNN, LSTM, CNN

Fabio Rovai

GAN trained on GAP clothes with super-resolution

GAN

Shortcut

A portrait created in ArtBreeder and augmented with a AICAN popart model

Artbreeder, AICAN

Shardcore

Generate a face with StyleGAN FFHQ, and use First Order Motion to animate a reading of William Blake's When Klopstock England Defied

First Order Motion, StyleGAN

Jürgen Schmidhuber

Create an artwork with the shortest algorithm while at the same time captures the essence of an object, using Kolmogorov Complexity

Occam's razor, Kolmogorov complexity

Sarah Meyohas

A GAN trained on a personal dataset of 100k individual petals and interpolated in a collage

GAN

Gene Kogan

Use Deep Painterly Harmonization to add objects to famous paintings

Deep Painterly Harmonization

Jennifer Walshe, Memo Akten

Train an audio RNN and GAN on Jennifer Walshe's video performances, and generate music and visuals real-time during a duet with the artist and model

Grannma Magnet, RNN, GAN

Kishi Yuma

GAN trained on pictures of hands

GAN

Ross Goodwin, Oscar Sharp

An LSTM generated screenplay trained on screenplays from several films and television series, and produced according to the screenplay

RNN, LSTM

Eric Lu

Classify a photo and match it with a doodle

CNN, Classification

Christian Mio Loclair, Waltz Binaire

GAN generated 3D sculpture and made in marble

GAN, Point Cloud

Mariel Pettee, Chase Shimmin, Douglas Duhaime, Ilya Vidrin

Generated choreography with VAEs trained on high-quality motion capture data of improvisational dance

VAE, RNN

Joanne Hastie

Paint 12 shapes, algorithmically combine the forms, use the Inception Classifier to select artworks, and then paint the final selection

CNN, Inception, Classification

David Ha

Use K-means to segment and colorize an image, inspired by Warhol

K-means

Dani Joy

An overpainted GAN interpolation of a smoking monkey

GAN

Nouf Aljowaysir

Using U-2 Net, the artist removed ‘oriental’ stereotypical figures in the dataset and then trained it on StyleGAN2 to signify the eradication of her ancestor’s collective memory

U-net, U-2 Net, StyleGAN

Josh Urban Davis

Creating Glitch art by modifying GAN weights

GAN, Weights

Robbie Barrat

GAN-generated Renaissance paintings using the WikiArt dataset

GAN, DCGAN

Mike Tyka

Class visualization of insects with DeepDream

DeepDream, Gradient Ascent

Submit projects here 💅

☞ ML x ART on Twitter

Copyright © 2021 Emil Wallner

All artworks © of their respective owners