Algebraic PDE and PDI characterization conjecture for polynomial neural-network spaces
Statement
Let be a feedforward neural network with inputs labeled by , and let and denote the polynomial functional spaces associated with the network, inside . Polynomial PDE and PDI characterization conjecture. There exist finitely many algebraic PDEs and algebraic PDIs such that, for sufficiently large , and the corresponding semi-algebraic subset of share a dense Zariski open subset; the same holds for the other polynomial functional spaces when every neuron of has fewer than inputs. This is the algebraic counterpart of the smooth characterization conjecture; the statement concerns generic polynomial functions and does not assert equality outside the shared dense Zariski open subset.
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.