search

IBM / LNN

A `Neural = Symbolic` framework for sound and complete weighted real-value logic
https://IBM.github.io/LNN/
Apache License 2.0
222 stars 433 forks source link

Creating example of LNNs with Traditional NN #59

Open anas-rz opened 1 year ago

anas-rz commented 1 year ago

Hi, We had a discussion with the IBM Neuro-Symbolic AI Team regarding contributing to LNN. One particular application type I became interested in is using them with traditional NN-based approaches. I suggest LNN repository should have some examples with public datasets like keras and Theseus. These examples help practitioners get a head-first experience of the framework. I look forward to contributing such one-click examples. Thanks.

buddha314 commented 1 year ago

Not the same thing, but the LTN library includes an example of using MNIST images and adding the numbers: https://github.com/logictensornetworks/logictensornetworks/tree/master/examples/mnist It's very hard to find integrated "neuro" and "semantic" (or "symbolic") examples.

I just created a test case I'd find fun: https://github.com/VerdantAI/math-blog/tree/master/nesy#trained-model-semantic-rules