DENSITY RESULTS BY DEEP NEURAL NETWORK OPERATORS WITH INTEGER WEIGHTS

In the present paper, a new family of multi-layers (deep) neural network (NN) operators is introduced. Density results have been established in space continuous functions on [−1,1], with respect to uniform norm. First, case two-layers considered detail, then definition and corresponding density extended general operators. All above definitions allow us prove approximation by constructive approach, sense that, for any given f all weights, thresholds, coefficients deep NN can be explicitly determined. Finally, examples activation provided, together graphical examples. The main motivation this work resides aim provide version well-known (shallow) operators, according what done applications construction models.