loss-functions
Here are 3 public repositories matching this topic...
A kind of neuralnet that runs in browser where each node smoothly chooses between many neural activation functions (sine tanh log exp + * arcsine etc) and is trained without backprop, instead using calculus directly on the sum of squared loss of all weights and all training data at once. Not GPU optimized yet.
-
Updated
Sep 8, 2023 - HTML
We aim to generate realistic images from text descriptions using GAN architecture. The network that we have designed is used for image generation for two datasets: MSCOCO and CUBS.
-
Updated
May 7, 2018 - HTML
Improve this page
Add a description, image, and links to the loss-functions topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the loss-functions topic, visit your repo's landing page and select "manage topics."