Joe-Naz01/loss_functions

Visualized logistic, hinge, and squared losses to compare optimization behavior. Demonstrated how curvature, smoothness, and margins influence model learning and convergence, linking each loss to real-world algorithms such as SVMs and logistic regression.

11
/ 100
Experimental
No License No Package No Dependents
Maintenance 6 / 25
Adoption 0 / 25
Maturity 5 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

—

License

—

Category

loss-function-implementations

Last pushed

Oct 23, 2025

Commits (30d)

0

GitHub
Loss Function Implementations · 36 frameworks

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Joe-Naz01/loss_functions"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

HelmchenLabSoftware/Cascade

Calibrated inference of spiking from calcium ΔF/F data using deep networks

58

adobe/antialiased-cnns

pip install antialiased-cnns to improve stability and accuracy

56

KaiyangZhou/pytorch-center-loss

Pytorch implementation of Center Loss

51

devsisters/pointer-network-tensorflow

TensorFlow implementation of "Pointer Networks"

51

kimhc6028/relational-networks

Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)

51

Explore ML Frameworks

All categories Trending ML Framework directory Insights