mirror of
https://github.com/Cian-H/symbolic_nn_tests.git
synced 2026-08-21 04:52:55 +01:00
Cian-H
ae14a1d7c0
Added a semantic function where the injected "knowledge" is just random garbage. This function was written to isolate the "knowledge" component of the other semantic functions, basically to ensure it's the matrices and not the rest of the process that is making the difference in training.
A sandbox for testing simple ways of injecting symbolic knowledge into neural networks.
This sandbox currently tests:
- Semantic loss functions