On the Use of Artificial Neural Networks for the Automated High-Level Design of ΣΔ Modulators P. Díaz-Lobo, G. Liñán-Cembrano and J.M. de la Rosa Journal Paper · IEEE Transactions on Circuits and Systems I: Regular Papers, 2023 abstractdoi
This paper presents a high-level synthesis methodology for Sigma-Delta Modulators (ΣΔ Ms) that combines behavioral modeling and simulation for performance evaluation, and Artificial Neural Networks (ANNs) to generate high-level designs variables for the required specifications. To this end, comprehensive datasets made up of design variables and performance metrics, generated from accurate behavioral simulations of different kinds of ΣΔ Ms, are used to allow the ANN to learn the complex relationships between design-variables and specifications. Several representative case studies are considered, including single-loop and cascade architectures with single-bit and multi-bit quantization, as well as both Switched-Capacitor (SC) and Continuous-Time (CT) circuit techniques. The proposed solution works in two steps. First, for a given set of specifications, a trained classifier proposes one of the available ΣΔ M architectures in the dataset. Second, for the proposed architecture, a Regression-type Neural Network (RNN) infers the design variables required to produce the requested specifications. A comparison with other optimization methods - such as genetic algorithms and gradient descent - is discussed, demonstrating that the presented approach yields to more efficient design solutions in terms of performance metrics and CPU time.
High-Level Design of Sigma-Delta Modulators using Artificial Neural Networks P. Díaz-Lobo and J.M. de la Rosa Journal Paper · IEEE International Symposium on Circuits and Systems ISCAS 2023
abstractdoi
This paper analyses the use of Artificial Neural Networks (ANNs) for the high-level synthesis and design of Sigma-Delta Modulators (ΣΔMs) . 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 ΣΔMs . Several ΣΔM 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 1 1 This work was supported in part by Grant PID2019-103876RB-I00, funded by MCIN/AEI/10.13039/501100011033, by the European Union ESF Investing in your future, and by ’’Junta de Andalucía’’ under Grant P20-00599.
