WALTZ-RES | Morphology & Dynamics of the loss landscape of gradient descent in a Resnet-25

Waltz-res visualizes the difference in morphology and dynamics between two small resnet-25 networks, one having skip connections and one not having them. In this visualization, we can see the first 2 and a half epochs of the training process.
More details and related analysis about this and other visualizations will be published in the future.
Loss Landscape generated with real data: resnet-25, imagenette dataset, sgd-adam, bs=16, bn, lr sched, train mod, 0.2 w range, log scaled (orig loss nums) & vis-adapted, net trained with fast.ai
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