Neural Network Approximation for Time Splitting Random Functions

In this article we present the multivariate approximation of time splitting random functions defined on a box or RN,N∈N, by neural network operators quasi-interpolation type. We achieve these approximations obtaining quantitative-type Jackson inequalities engaging modulus continuity related function its partial high-order derivatives. use density to define our operators. These derive from logistic and hyperbolic tangent sigmoid activation functions. Our convergences are both point-wise uniform. The engaged feed-forward networks possess one hidden layer. finish with great variety applications.