RF-LNA circuit synthesis by genetic algorithm-specified artificial neural network

Dumesnil, Etienne; Nabki, Frédéric; Boukadoum, Mounir

doi:10.1109/icecs.2014.7050096

Cited by 9 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [32], the core idea was to delegate part of the NN design to a genetic algorithm (GA) that iterated to decide on the following: the neural network type (multi-layer perceptron or radial-basis function) and which performance metrics and which design constraints to include as the input features during training. The GA was actually given a set of performance specifications and some additional design constraints: the algorithm worked by feeding consecutively several subsets of the two previous variables to the NN, thus removing and adding input elements depending on the training and validation results.…”

Section: Hybrid Ic Design Automation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Machine Learning Techniques in Analog Integrated Circuit Design Automation

Mina

Jabbour

Sakr³

2022

Electronics

View full text Add to dashboard Cite

Analog integrated circuit design is widely considered a time-consuming task due to the acute dependence of analog performance on the transistors’ and passives’ dimensions. An important research effort has been conducted in the past decade to reduce the front-end design cycles of analog circuits by means of various automation approaches. On the other hand, the significant progress in high-performance computing hardware has made machine learning an attractive and accessible solution for everyone. The objectives of this paper were: (1) to provide a comprehensive overview of the existing state-of-the-art machine learning techniques used in analog circuit sizing and analyze their effectiveness in achieving the desired goals; (2) to point out the remaining open challenges, as well as the most relevant research directions to be explored. Finally, the different analog circuits on which machine learning techniques were applied are also presented and their results discussed from a circuit designer perspective.

show abstract

Section: Hybrid Ic Design Automation Methodsmentioning

confidence: 99%

“…Hybrid methods combining global optimization and NN were proposed in [32][33][34][35][36][37]. These techniques achieve enhanced results compared to pure multi-objective optimization methods, at a lower computation time.…”

mentioning

confidence: 99%

A Review of Machine Learning Techniques in Analog Integrated Circuit Design Automation

Mina

Jabbour

Sakr³

2022

Electronics

View full text Add to dashboard Cite

show abstract

“…The reason for conducting the experiment came from the literature suggesting that redundancy in an ANN's input may impede its performance [7]. The idea of dealing with this issue by letting the GA select which inputs to include in the ANN definition was suggested in [4] with promising results, and it was thus considered here. However, our simulations showed that the method did not decrease the learning time, which remained approximately the same as before.…”

Section: Discussionmentioning

confidence: 99%

“…The circuit topology for realizing the RF-LNA is the same as in [3] and [4], and it is presented in Fig. 2.…”

Section: A Radiofrequency Low Noise Amplifiermentioning

confidence: 99%

RF-LNA circuit synthesis using an array of artificial neural networks with constrained inputs

Dumesnil

Nabki

Boukadoum

2015

2015 IEEE International Symposium on Circuits and Systems (ISCAS)

Self Cite

View full text Add to dashboard Cite

Abstract-We describe a method for circuit synthesis that determines the parameter values by using a set of artificial neural networks (ANNs) that learn in sequence. Each ANN is optimized to output only one design parameter, and the latter constrains the learning/recall of its successor(s). Two competing ANN architectures are considered, the multilayer perceptron (MLP) and the radial basis functions (RBF) network, and each one has its internal parameters tuned by a genetic algorithm. The method was tested on the design of a radio-frequency, low-noise amplifier (RF-LNA) with ten design parameters to set, and it yielded one-hundred percent success rate in specifying the parameter values at five percent tolerance.Keywords-Synthesis, artificial neural network, genetic algorithm, multilayer perceptron, radial basis function, radiofrequency low noise amplifier.

show abstract

“…In most cases, ML was introduced for the prediction of efficiency metrics for a design while, in some other cases, for design parameters prediction. For example, in [11], a feed-forward artificial neural network (ANN) for the synthesis of a radio-frequency, low noise amplifier (RF-LNA) circuit was proposed in combination with a GA for the optimal ANN architecture selection and input parameters tuning. Additionally, in [12], taking advantage of Bayesian linear regression and support vector machine models, an accelerated algorithm to explore the analog circuit performance limitations on the required technology was introduced.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid GA/ML-Based End-to-End Automated Methodology for Design Acceleration of Wireless Communications CMOS LNAs

et al. 2023

View full text Add to dashboard Cite

A new methodology for the RF/mmWave analog design process, automation and acceleration, is presented in this work. The proposed framework was implemented so as to accelerate the design cycle of analog/RF circuits by creating a dataset in a fully automated manner and training a combination of machine learning models for the optimal design parameters’ prediction. machine learning polynomial regression was adopted to accelerate the design process, predicting the optimal design parameters’ values while genetic algorithm optimization was exploited for the dataset creation automation. To evaluate the efficiency of the proposed methodology, the framework was implemented for the design of a common source Low-Noise-Amplifier, using a 65 nm CMOS process node. The proposed methodology successfully tackles the design cycle speed-up, automation, and acceleration, utilizing machine learning prediction for the design parameters and genetic algorithm for the dataset creation automation instead of the classical, simulation-based, standard design methodology. The provided experimental results have shown the effectiveness of the proposed hybrid approach, creating very precise RF matching networks for LNA designs and achieving >99.9% wave transmission efficiency while reaching >99% accuracy on the parameters’ prediction task.

show abstract

RF-LNA circuit synthesis by genetic algorithm-specified artificial neural network

Cited by 9 publications

References 8 publications

A Review of Machine Learning Techniques in Analog Integrated Circuit Design Automation

A Review of Machine Learning Techniques in Analog Integrated Circuit Design Automation

RF-LNA circuit synthesis using an array of artificial neural networks with constrained inputs

A Hybrid GA/ML-Based End-to-End Automated Methodology for Design Acceleration of Wireless Communications CMOS LNAs

Contact Info

Product

Resources

About