Local PDE and PDI sufficiency conjecture for neural networks
Statement
Let be a feedforward neural network with inputs labeled by the coordinate functions , and let be smooth near a point . Write for the corresponding partial derivatives. In either setting covered by the paper's two main theorems, Local PDE and PDI sufficiency conjecture. There exist finitely many non-vanishing conditions , finitely many algebraic PDEs , and finitely many algebraic PDIs such that, for every , the non-vacuous space of smooth function germs near computable by and satisfying the non-vanishing conditions at is characterized by those PDEs and PDIs. This is a local sufficiency conjecture for the necessary differential constraints proved earlier; the required conditions and a general proof remain open.
Record
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.