A library provides integration between Domain Knowledge and Deep Learning.
Project description
The library allows to specify a problem domain with a conceptual graph including declarations of edges and nodes, as well as logical constraints on the graph concepts and relations. Neural network outputs bounded to the graph edges and nodes. The logical constraints are converted to ILP and Gurobi Solver is used for inferring. This adds a relational overlay over elements in a network that relates physical concepts in applications.
The example running in Google CoLab environment, presenting the usage of the library is here.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file DomiKnowS-0.520.dev0.tar.gz.
File metadata
- Download URL: DomiKnowS-0.520.dev0.tar.gz
- Upload date:
- Size: 135.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.8.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a08ca4be1c8c23224518df41d26807c19f484dbe96f6fcd4775ce8b5ada7fc68
|
|
| MD5 |
95e751de0510e4a6f0a138d699e59cd0
|
|
| BLAKE2b-256 |
aa86b89dcc946141872a6c246892085cfd702033e251dabc754791412a27c761
|
File details
Details for the file DomiKnowS-0.520.dev0-py3-none-any.whl.
File metadata
- Download URL: DomiKnowS-0.520.dev0-py3-none-any.whl
- Upload date:
- Size: 164.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.8.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ce57a17521a7a668f00831d277f7e420707a3be66d7a81e0116b1299ff7c5c8d
|
|
| MD5 |
c588b80662e250caa6cd02cf4a2cf177
|
|
| BLAKE2b-256 |
97d0997ea7ed392b62e678b2c557f272abdf9346423c7c9e0e9192f91ee3fe7a
|
