Image-focused

Project We investigate the possibilities to identify motion as a continuous walk in a latent space of situations. Blackberry Winter is a triptych of artificial human motion in asymmetry. We developed three different choreographies of human bodies and their ongoing neural relationship in reference to each other, using our custom machine learning solution to weave spatial information into contemporary GAN technology. Technology We developed a custom Generative Adversarial Network pipeline called RayGan to teach our network a possibility space of human poses. …

Klingemann applies deep learning techniques in an attempt to discover new forms of aesthetics - and blur the lines between human and machine creativity. He has used image-focused neural network architectures since the release of Deep Dream. Style transfer, ppgn, pix2pix and [CycleGAN] are architectures he has investigated and experimented with in an artistic context. Klingemann showed several of his “Neurographer” works at Ars Electronica 2017. [CycleGAN] The CycleGAN is a technique that involves the automatic training of image-to-image translation models without paired examples. …