LATENT | Wasserstein GP GAN Loss Landscape morphology dyn

VIDEO DESCRIPTION:

Play, download and edit the free video LATENT | Wasserstein GP GAN Loss Landscape morphology dynamics visualization.

LATENT visualizes the initial stages of the training of a Wasserstein GP GAN network, trained over the celebA dataset. the first part of the video shows the first 1K steps of the training, and the final part shows the steps from 10K to 11K.

Loss Landscape generated with real data: wasserstein GP Gan, celebA dataset, sgd-adam, bs=64, train mod, 300k pts, 1 w range, latent space dimensions: 200, generator is sometimes reversed for visual purposes, critic is log scaled (orig loss nums) & vis-adapted, net trained with fast.ai and pytorch

In the intersection between research and art, the A.I LL project explores the morphology and dynamics of the fingerprints left by deep learning optimization training processes.

The project goes deep into the training phase of these processes and generates high quality visualizations, using some of the latest deep learning and machine learning research and producing inspiring animations that can both inform and inspire the community.

As the weight space changes through the optimization process, loss landscapes become alive, organic entities that challenge us to unlock the mysteries of learning.

How do these multidimensional entities behave and change as we modify hyperparameters and other elements of our networks?

How can we best tame these wild beasts as we cross their edge horizon on our way to the deepest convexity they hold?

losslandscape.com

Download, play and edit free videos and free audios from LATENT | Wasserstein GP GAN Loss Landscape morphology dynamics visualization using RedcoolMedia.net web apps