This paper analyses the use of Artificial Neural Networks (ANNs) for the high-level synthesis and design of Sigma-Delta Modulators (SDMs). The presented methodology is based on training ANNs to identify optimum design patterns, so that they can learn to predict the best set of design variables for a given set of specifications. This strategy has been successfully applied in prior works to design basic analog building blocks, and it is explored in this work to automate the high-level sizing of SDMs. Several SDM case studies, which include both single- loop and cascade topologies as well as Switched-Capacitor (SC) and Continuous-Time (CT) circuit techniques are shown. The effect of ANN hyperparameters – such as the number of layers, neurons per layer, batch size, number of epochs, etc. - is analyzed in order to find out the best ANN architecture that finds an optimum design with less computational resources. A comparison with other optimization methods - such as genetic algorithms and gradient descent - is shown, demonstrating that the presented approach yields to more efficient design solutions in terms of performance metrics, power consumption and CPU time.