I had done semantic similarity to identify duplicate questions in data set using LSTM networks in python jupyter notebook. Now i want to do this task on neo4j to build knowledge graphs.
Principles of deep learnings are the same in all platforms. You just need to define nodes, define more layers (deep learning), define weights, then design your learning protocols, as you wish, and of-course you need an initial database and iteration databases, however your trainings and application might be, that would change.
The key is to first install and get to know neo, then step by step follow forward, if you have details tech questions, put it on stackoverflow.com, there are adept AI engineers in there, will respond quickly, once you have your trial codes.