However, it degenerates to ~KAN if restring to pairwise dependencies (can consciously add triplewise and higher), and gives many new possibilities, like multidirectional propagation, of values or probability distributions, with novel additional training approaches like through tensor decomposition.
There are a lot of ideas that are clever and seem promising... but fail to perform well on such benchmarks.
Is there a github repo with code available?
Multidirectional are biological neurons, but I don't know how to compare with them?
---
To be 100% clear: My question about practical application today is orthogonal to the question about whether this research is worth pursuing!
And no, recreating it is not a task a single person can complete.
And for pairwise distribution becomes ~KAN, which turned out quit successful ... so we are talking about its extension: adding more possibilities, like triplewise dependencies and multidirectional propagation.
Doesn't look like it.