Data Sculpture

Data Sculpturing translates our indescribable subjects or creativity to a latent vector and re-create the output to amplify the creators' creativity by machine learning. The latent space of big data provides a higher dimension of creativity by creating a new medium for people to sculpture their imagination and experience. This is because people can use machine learning to extract information from the enormous datasets collected from mobile devices. In other words, artists sculpture thier own work from the data of their experience. Below are some artwork that I experience with SOTA deep learning algorithm.

Style Transfer Learning

Neural style transfer is an optimization technique used to take three images, a content image, a style reference image (such as an artwork by a famous painter), and the input image you want to style — and blend them together such that the input image is transformed to look like the content image, but “painted” in the style of the style image.

GENERATIVE ADVERSARIAL NETWORKS

Generative Adversarial Neural Networks (GANs) are a type of neural network that can generate random “fake” images based on a training set of real images. GANs were introduced by Ian Goodfellow in his 2014 paper. I used the model of StyleGAN ADA released by Nvidia to sculpture my own experience. The model was trained by 1.8k images of abstract and fluid art. An animation of morphyic images interpolate the sense of time and space with an indescripable experience.