Z80coder/db-nets

∂B nets: learning discrete, boolean-valued functions by gradient descent

22
/ 100
Experimental

This is a neural network library for machine learning researchers and practitioners working on novel network architectures. It helps in training neural networks that produce clear 'yes/no' or 'true/false' answers rather than probabilities. You input discrete, boolean-valued functions, and it outputs trained models that are also boolean-valued.

No commits in the last 6 months.

Use this if you are developing neural networks and need to ensure your model's outputs are definitive boolean values, suitable for logic-based decision making, rather than continuous or probabilistic scores.

Not ideal if your problem requires continuous output values, standard probabilistic classification, or if you are not comfortable with deep learning research frameworks like Flax and JAX.

neural-network-research boolean-logic-modeling discrete-function-learning AI-architecture-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

21

Forks

2

Language

Mathematica

License

Last pushed

Jan 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Z80coder/db-nets"

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