View allAll Photos Tagged machinelearning
A digital image 'dreamed by' Midjourney, an artificial intelligence program that creates images from textual descriptions.
A digital image 'dreamed by' Midjourney, an artificial intelligence program that creates images from textual descriptions.
A digital image 'dreamed by' Midjourney, an artificial intelligence program that creates images from textual descriptions.
A digital image 'dreamed by' Midjourney, an artificial intelligence program that creates images from textual descriptions.
Generated by MidJourney for Aaron Ximm, v3 engine, late July 2022; prompt: "intricate colorful ::burning-man-festival, illustrations, botanical illustration, earthy palette, natural dyes. Volumetric shading. Many species. Colored pencil and water color. Isometric false perspective. Long shot. Style of Rousseau, Seuss, Sendak, Arts-and-Crafts. The playa at golden hour. --ar 3:2"
a gridded 2d visualization of 1,728 pictures of animals clustered by similarity using t-SNE. each of the images are first encoded into 4096-bit feature vector derived from the activations of the last fully-connected layer in a convolutional neural network. Then the features are reduced to 2d using t-SNE dimensionality reduction technique, and then gridded using RasterFairy.
software used:
github.com/kylemcdonald/ofxCcv/
github.com/Quasimondo/RasterFairy
images downloaded from Caltech-256:
www.vision.caltech.edu/Image_Datasets/Caltech256/images/
animals include:
bat, bear, bonsai*, butterfly, cactus*, camel, centipede, chimp, cockroach, conch, crab, dog, dolphin, duck, elephant, elk, fern*, frog, giraffe, goat, goose, gorilla, grasshopper, hawksbill, hibiscus, horse, horseshoe-crab, house-fly, iguana, hummingbird, ibis, iris, killer-whale, kangaroo, llama, mushroom*, octopus, ostrich, owl, penguin, porcupine, praying-mantis, raccoon, scorpion, skunk, snake, snail, spider, starfish*, sunflower, swan, greyhound, trilobite, unicorn, zebra, toad, triceratops
* i know some of these are technically not in the animal kingdom
In the Ars Electronica Center's Machine Learning Studio visitors can use computer vision and machine learning applications to discover how machines learn and perceive their environment. Working with tech trainers, they can build and train self-driving model cars here, program robots with facial recognition, and gain insights into how they can teach these devices a wide variety of activities. Step-by-step, they can experience not only how these technologies function, but also that everything the machines know is determined by us.
Ars Electronica Center Linz
Ars-Electronica-Straße 1
4040 Linz
Austria
Credit: Ars Electronica - Magdalena Sick-Leitner