KENN (Knowledge Enhanced Neural Networks) is a library for python 2.7 built on top of TensorFlow which permits to enhance neural networks models with logical constraints (clauses). It does so by adding a new final layer, called Knowledge Enhancer (KE), to the existing neural network. The KE change the orginal predictions of the standard neural network enforcing the satisfaction of the constraints. Additionally, it contains clause weights, learnable parameters associated to the constraints that represent their strength.
1 maintainer
Metadata
1 maintainer
Release files for kenn 1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| kenn-1.0.tar.gz | 3.8 kB | Details |
Release files / kenn-1.0.tar.gz
| Download URL | kenn-1.0.tar.gz |
|---|---|
| Size | 3.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
08bf0a598ed0578c2fc02aabfd47b2d1b42f9bf48913891e6b1fd582808e0039
|
|
BLAKE2b-256 checksum How to use checksums |
00c57a88248e6740bf71c085f6dc51a979406a6b5463f8bd4614720a4870b22e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.13.0 pkginfo/1.5.0.1 requests/2.14.2 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/2.7.13
|
