halleyscommet said:
Do you not have enough confidence in the theory to publish it without first having proven it experimentally? Do you have some sort of moral, ethical or philosophical objection to publishing a purely theoretical paper?
Bengio, a pioneer in
Deep Learning can have the leisure of posting papers on major peer reviewed journals, even without any semblance of experimental results. (An example is his recent
Consciousness Prior Paper)
I am not a pioneer in machine learning, nor do I have a machine learning degree, so I don't have the same leisure as Bengio.
halleyscommet said:
It occurs to me, the work needed to break your overall theory down into a project that could be executed on a grid computing platform would itself constitute a publishable paper.
You seem to have put yourself in an interesting chicken and egg situation. You’re unwilling to publish a theoretical paper but without a theoretical paper you’re unlikely to get the grants needed to purchase the hardware to do the experiments you want to do. To make progress forward you need either publish a theoretical paper or break down your theory so that it can be run on a grid computing platform.
What is your plan?
That occurrence is wrong...
An initial, albeit substantial degree of the
structure to be tested, shall align with the requirements I priorly mentioned
here.