Multidirectional joint distribution neurons reducing to KAN
arxiv.org
arxiv.org
Also, while current ANNs use guessed parametrizations, objectively available is joint distribution - biological neuron should be evolutionarily optimized to exploit, and it is relatively simple in approach from this arXiv.
Such joint distribution neurons bring additional training approaches - maybe some of them are used by biological neural networks?
>for biological neurons e.g. "it is not uncommon for axonal propagation of action potentials to happen in both directions" - suggesting they are optimized to continuously operate in multidirectional way.
What is true is that dendritic spikes can propagate bidirectionally in some neurons (but can also fade or be blocked).
What we often forget is that spikes are a kludge to enable faster INTRAcellular communication (not needed in retinal processing).
The classic action potential connects the axon hillock (the spike initiation zone) to a variable subset of responsive presynaptic sites that may or may not release neurotransmitters that may or may not modulate behaviors of neighboring processes and cells.
In contrast, current ANNs are focused on unidirectional propagation, and are much worse at training from single samples - to reach abilities of biological, maybe it is worth to start thinking about multidirectional?
Neurons containing joint distribution model can do propagate conditional distributions in various direction, and it is not that difficult to represent - maybe something like that could be hidden in biological (?)
Doesn't look like it.
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.