You're currently viewing an old version of this dataset. To see the current version, click here.

Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT

Three benchmark datasets: Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT, created by training convolutional, residual, and vision transformer architectures from scratch with 2,913 systematically generated activation functions.

Data and Resources

Cite this as

Garrett Bingham, Risto Miikkulainen (2024). Dataset: Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT. https://doi.org/10.57702/eqxd1cv2

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Garrett Bingham
More Authors
Risto Miikkulainen
Homepage https://github.com/cognizant-ai-labs/act-bench