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

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

- Neural networks (NNs) of different complexities (shallow and deep) using both supervised [10,11,12,13,14,15,16,17,18] and reinforcement [19,20,21] learning techniques have been proposed in the past six years. These methods have been boosted by the progress in the development of high-performance computing hardware and are gaining attention in the scientific community thanks to their ability to model complex nonlinear problems [22];
- Multi-objective optimization with several heuristic- and stochastic-assisted strategies to explore the search space efficiently: Bayesian [23,24], particle swarm [25], the Gaussian process [26], simulated annealing [27], and genetic algorithms [28,29,30]. These are simulation-based optimizations that rely on a circuit simulator to find a solution. Although global optimization is not an ML technique in the strict sense of the word, it remains a powerful mathematical tool for the automation of circuit design. In contrast, older equation-based techniques as in [31] are no longer considered;

## 2. NN-Based IC Design Automation Methods

#### 2.1. Supervised Learning

- Dataset generation technique;
- Feature selection;
- NN complexity;
- IC fabrication process used;
- Types of circuits targeted;
- Result validation method.

#### 2.1.1. Dataset Generation Technique

#### 2.1.2. Feature Selection

#### 2.1.3. NN Complexity

#### 2.1.4. IC Fabrication Process

#### 2.1.5. Target Circuits

#### 2.1.6. Result Validation Method

#### 2.2. Reinforcement Learning

## 3. Hybrid IC Design Automation Methods

## 4. Discussion and Analysis

#### 4.1. Analysis of the Previous Learning Approaches

#### 4.2. Analysis of Circuit Features

#### 4.3. Transistor Biasing Considerations

## 5. Open Challenges in the Field

## 6. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Gray, P.R.; Hurst, P.J.; Lewis, S.H.; Meyer, R.G. Analysis and Design of Analog Integrated Circuits, 6th ed.; Wiley Publishing: Hoboken, NJ, USA, 2017. [Google Scholar]
- Lavagno, L.; Martin, G.; Scheffer, L. Electronic Design Automation for Integrated Circuits Handbook, 2nd ed.; CRC Press: Boca Raton, FL, USA, 2016. [Google Scholar]
- Toledo, P.; Rubino, R.; Musolino, F.; Crovetti, P. Re-Thinking Analog Integrated Circuits in Digital Terms: A New Design Concept for the IoT Era. IEEE Trans. Circuits Syst. II Express Briefs
**2021**, 68, 816–822. [Google Scholar] [CrossRef] - Aiello, O.; Crovetti, P.; Alioto, M. Fully Synthesizable Low-Area Analogue-to-Digital Converters with Minimal Design Effort Based on the Dyadic Digital Pulse Modulation. IEEE Access
**2020**, 8, 70890–70899. [Google Scholar] [CrossRef] - Rémond, E.; Nercessian, E.; Bernicot, C.; Mina, R. Mathematical approach based on a “Design of Experiment” to simulate process variations. In Proceedings of the 2011 Design, Automation and Test in Europe, Grenoble, France, 14–18 March 2011; pp. 1–5. [Google Scholar]
- Joet, L.; Dezzani, A.; Montaudon, F.; Badets, F.; Sibille, F.; Corre, C.; Chabert, L.; Mina, R.; Bailleuil, F.; Saias, D.; et al. Advanced ‘Fs/2’ Discrete-Time GSM Receiver in 90-nm CMOS. In Proceedings of the 2006 IEEE Asian Solid-State Circuits Conference, Hangzhou, China, 13–15 November 2006; pp. 371–374. [Google Scholar] [CrossRef]
- Montaudon, F.; Mina, R.; Tual, S.L.; Joet, L.; Saias, D.; Hossain, R.; Sibille, F.; Corre, C.; Carrat, V.; Chataigner, E.; et al. A Scalable 2.4-to-2.7GHz Wi-Fi/WiMAX Discrete-Time Receiver in 65nm CMOS. In Proceedings of the 2008 IEEE International Solid-State Circuits Conference—Digest of Technical Papers, San Francisco, CA, USA, 3–7 February 2008; pp. 362–619. [Google Scholar] [CrossRef]
- Nguyen, M.T.; Jabbour, C.; Ouffoue, C.; Mina, R.; Sibille, F.; Loumeau, P.; Triaire, P.; Nguyen, V.T. Direct delta-sigma receiver: Analysis, modelization and simulation. In Proceedings of the 2013 IEEE International Symposium on Circuits and Systems (ISCAS), Beijing, China, 19–23 May 2013; pp. 1035–1038. [Google Scholar] [CrossRef]
- Wagner, G.; Mina, R. Amplifier for Wireless Receiver. 2015. Available online: https://patentimages.storage.googleapis.com/ca/21/0b/4bc82b44df4daa/US9077302.pdf (accessed on 13 January 2022).
- Vural, R.A.; Kahraman, N.; Erkmen, B.; Yildirim, T. Process independent automated sizing methodology for current steering DAC. Int. J. Electron.
**2015**, 102, 1713–1734. [Google Scholar] [CrossRef] - Lohit, V.B.; Pandey, N.; Bhattacharyya, A. Modeling and Design of Inverter Threshold Quantization Based Current Comparator using Artificial Neural Networks. Int. J. Electr. Comput. Eng.
**2016**, 6, 320–329. [Google Scholar] [CrossRef] - Hasani, R.M.; Haerle, D.; Baumgartner, C.F.; Lomuscio, A.R.; Grosu, R. Compositional neural-network modeling of complex analog circuits. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, 14–19 May 2017; pp. 2235–2242. [Google Scholar] [CrossRef] [Green Version]
- Fukuda, M.; Ishii, T.; Takai, N. OP-AMP sizing by inference of element values using machine learning. In Proceedings of the 2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Xiamen, China, 6–9 November 2017; pp. 622–627. [Google Scholar] [CrossRef]
- Wang, Z.; Luo, X.; Gong, Z. Application of Deep Learning in Analog Circuit Sizing. In Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence, Shenzhen, China, 8–10 December 2018; pp. 571–575. [Google Scholar] [CrossRef]
- Lourenço, N.; Rosa, J.; Maryins, R.; Aidos, H.; Canelas, A.; Póvoa, R.; Horta, N. On the Exploration of Promising Analog IC Designs via Artificial Neural Networks. In Proceedings of the 2018 15th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD), Prague, Czech Republic, 2–5 July 2018; pp. 133–136. [Google Scholar] [CrossRef]
- Harsha, M.; Harish, B.P. Artificial Neural Network Model for Design Optimization of 2-stage Op-amp. In Proceedings of the 2020 24th International Symposium on VLSI Design and Test (VDAT), Bhubaneswar, India, 23–25 July 2020; pp. 1–5. [Google Scholar] [CrossRef]
- Murphy, S.D.; McCarthy, K.G. Automated Design of CMOS Operational Amplifier Using a Neural Network. In Proceedings of the 2021 32nd Irish Signals and Systems Conference (ISSC), Athlone, Ireland, 10–11 June 2021; pp. 1–6. [Google Scholar] [CrossRef]
- Grabmann, M.; Feldhoff, F.; Gläser, G. Power to the Model: Generating Energy-Aware Mixed-Signal Models using Machine Learning. In Proceedings of the 2019 16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design, Lausanne, Switzerland, 15–18 July 2019; pp. 5–8. [Google Scholar] [CrossRef]
- Wang, H.; Yang, J.; Lee, H.S.; Han, S. Learning to Design Circuits. arXiv
**2018**, arXiv:abs/1812.02734. [Google Scholar] - Settaluri, K.; Haj-Ali, A.; Huang, Q.; Hakamaneshi, K.; Nikolic, B. AutoCkt: Deep Reinforcement Learning of Analog Circuit Designs. In Proceedings of the 2020 Design, Automation Test in Europe Conference Exhibition (DATE), Grenoble, France, 9–13 March 2020; pp. 490–495. [Google Scholar] [CrossRef]
- Zhao, Z.; Zhang, L. Deep Reinforcement Learning for Analog Circuit Sizing. In Proceedings of the 2020 IEEE International Symposium on Circuits and Systems (ISCAS), Seville, Spain, 12–14 October 2020; pp. 1–5. [Google Scholar]
- Russell, S.J.; Norvig, P. Artificial Intelligence: A Modern Approach, 3rd ed.; Pearson: London, UK, 2009. [Google Scholar]
- Lyu, W.; Xue, P.; Yang, F.; Yan, C.; Hong, Z.; Zeng, X.; Zhou, D. An Efficient Bayesian Optimization Approach for Automated Optimization of Analog Circuits. IEEE Trans. Circuits Syst. I
**2018**, 65, 1954–1967. [Google Scholar] [CrossRef] - Lyu, W.; Yang, F.; Yan, C.; Zhou, D.; Zeng, X. Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design. In Proceedings of the 35th International Conference on Machine Learning, PMLR, Stockholm, Sweden, 10–15 July 2018; Volume 80, pp. 3306–3314. [Google Scholar]
- Rout, P.K.; Acharya, D.P.; Panda, G. A Multiobjective Optimization Based Fast and Robust Design Methodology for Low Power and Low Phase Noise Current Starved VCO. IEEE Trans. Semicond. Manuf.
**2014**, 27, 43–50. [Google Scholar] [CrossRef] - Liu, B.; Zhao, D.; Reynaert, P.; Gielen, G.G.E. GASPAD: A General and Efficient mm-Wave Integrated Circuit Synthesis Method Based on Surrogate Model Assisted Evolutionary Algorithm. IEEE Trans. -Comput.-Aided Des. Integr. Circuits Syst.
**2014**, 33, 169–182. [Google Scholar] [CrossRef] - Martins, R.; Lourenço, N.; Póvoa, R.; Horta, N. Shortening the gap between pre- and post-layout analog IC performance by reducing the LDE-induced variations with multi-objective simulated quantum annealing. Eng. Appl. Artif. Intell.
**2021**, 98, 104102. [Google Scholar] [CrossRef] - Rojec, Z.; Bűrmen, Á.; Fajfar, I. Analog circuit topology synthesis by means of evolutionary computation. Eng. Appl. Artif. Intell.
**2019**, 80, 48–65. [Google Scholar] [CrossRef] - Okochi, K.; Takai, N.; Sugawara, Y.; Suzuki, K.; Yoshizawa, S.; Kobayashi, H. Automatic design of operational amplifier by combination method of function block. In Proceedings of the 2016 13th IEEE International Conference on Solid-State and Integrated Circuit Technology (ICSICT), Hangzhou, China, 25–28 October 2016; pp. 965–967. [Google Scholar] [CrossRef]
- Negishi, T.; Arai, N.; Takai, N.; Kato, M.; Seki, H.; Kobayashi, H. Automatic Synthesis of Comparator Circuit Using Genetic Algorithm and SPICE Optimizing Function. Key Eng. Mater.
**2015**, 643, 131–140. [Google Scholar] [CrossRef] - Hjalmarson, E.; Hagglund, R.; Wanhammar, L. An equation-based optimization approach for analog circuit design. In Proceedings of the Signals, Circuits and Systems, SCS 2003, International Symposium on, Iasi, Romania, 10–11 July 2003; Volume 1, pp. 77–80. [Google Scholar] [CrossRef]
- Dumesnil, E.; Nabki, F.; Boukadoum, M. RF-LNA circuit synthesis by genetic algorithm-specified artificial neural network. In Proceedings of the 2014 21st IEEE International Conference on Electronics, Circuits and Systems (ICECS), Marseille, France, 7–10 December 2014; pp. 758–761. [Google Scholar] [CrossRef]
- Lourenço, N.; Afacan, E.; Martins, R.; Passos, F.; Canelas, A.; Póvoa, R.; Horta, N.; Dundar, G. Using Polynomial Regression and Artificial Neural Networks for Reusable Analog IC Sizing. In Proceedings of the 2019 16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD), Lausanne, Switzerland, 15–18 July 2019; pp. 13–16. [Google Scholar] [CrossRef]
- Hakhamaneshi, K.; Werblun, N.; Abbeel, P.; Stojanovic, V. BagNet: Berkeley Analog Generator with Layout Optimizer Boosted with Deep Neural Networks. In Proceedings of the 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Westminster, CO, USA, 4–7 November 2019; pp. 1–8. [Google Scholar] [CrossRef] [Green Version]
- İslamoğlu, G.; Çakici, T.O.; Afacan, E.; Dündar, G. Artificial Neural Network Assisted Analog IC Sizing Tool. In Proceedings of the 2019 16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD), Lausanne, Switzerland, 15–18 July 2019; pp. 9–12. [Google Scholar] [CrossRef]
- Gao, Z.; Tao, J.; Su, Y.; Zhou, D.; Zeng, X. Efficient Performance Trade-off Modeling for Analog Circuit based on Bayesian Neural Network. In Proceedings of the 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Westminster, CO, USA, 4–7 November 2019; pp. 1–8. [Google Scholar] [CrossRef]
- Li, Y.; Wang, Y.; Li, Y.; Zhou, R.; Lin, Z. An Artificial Neural Network Assisted Optimization System for Analog Design Space Exploration. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.
**2020**, 39, 2640–2653. [Google Scholar] [CrossRef] - Passos, F.; Roca, E.; Castro-López, R.; Fernández, F.V. A Comparison of Automated RF Circuit Design Methodologies: Online Versus Offline Passive Component Design. IEEE Trans. Very Large Scale Integr. (VLSI) Systems
**2018**, 26, 2386–2394. [Google Scholar] [CrossRef] - Wei, P.H.; Murmann, B. Analog and Mixed-Signal Layout Automation Using Digital Place-and-Route Tools. IEEE Trans. Very Large Scale Integr.n (VLSI) Systems
**2021**, 29, 1838–1849. [Google Scholar] [CrossRef] - Afacan, E.; Lourenço, N.; Martins, R.; Dündar, G. Review: Machine learning techniques in analog/RF integrated circuit design, synthesis, layout, and test. Integration
**2021**, 77, 113–130. [Google Scholar] [CrossRef] - Fayazi, M.; Colter, Z.; Afshari, E.; Dreslinski, R. Applications of Artificial Intelligence on the Modeling and Optimization for Analog and Mixed-Signal Circuits: A Review. IEEE Trans. Circuits Syst. Regul. Pap.
**2021**, 68, 2418–2431. [Google Scholar] [CrossRef] - Khailany, B.; Ren, H.; Dai, S.; Godil, S.; Keller, B.; Kirby, B.; Klinefelter, A.; Venkatesan, R.; Zhang, Y.; Catanzaro, B.; et al. Accelerating Chip Design With Machine Learning. IEEE Micro
**2020**, 40, 23–32. [Google Scholar] [CrossRef] - Aggarwal, C.C. Neural Networks and Deep Learning, 3rd ed.; Springer International: Berlin/Heidelberg, Germany, 2018. [Google Scholar]
- Wolfe, G.; Vemuri, R. Extraction and use of neural network models in automated synthesis of operational amplifiers. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.
**2003**, 22, 198–212. [Google Scholar] [CrossRef] - Carusone, T.C.; Johns, D.; Martin, K. Analog Integrated Circuit Design, 2nd ed.; John Wiley and Sons Inc.: Hoboken, NJ, USA, 2012. [Google Scholar]
- Wang, H.; Wang, K.; Yang, J.; Shen, L.; Sun, N.; Lee, H.-S.; Han, S. GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning. 2020. Available online: https://arxiv.org/abs/2005.00406 (accessed on 13 January 2022).
- Nassif, H.; Costa, V.S.; Burnside, E.S.; Page, D. Relational Differential Prediction. In Machine Learning and Knowledge Discovery in Databases; Flach, P.A., De Bie, T., Cristianini, N., Eds.; Springer: Berlin/Heidelberg, Germany, 2012; pp. 617–632. [Google Scholar]
- Dehbashian, M.; Maymandi-Nejad, M. An enhanced optimization kernel for analog IC design automation using the shrinking circles technique. Eng. Appl. Artif. Intell.
**2017**, 58, 62–78. [Google Scholar] [CrossRef] - Ding, M.; Harpe, P.; Chen, G.; Busze, B.; Liu, Y.H.; Bachmann, C.; Philips, K.; van Roermund, A. A Hybrid Design Automation Tool for SAR ADCs in IoT. IEEE Trans. Very Large Scale Integr. (VLSI) Syst.
**2018**, 26, 2853–2862. [Google Scholar] [CrossRef] [Green Version]

**Figure 3.**Description of the training-dataset-generation approach used in [13].

**Figure 6.**Conceptual bloc diagram of the hybrid technique used in [33].

**Figure 7.**Schematic of the cascode low-noise amplifier circuit used in [32].

**Figure 8.**Bloc diagram of the hybrid approach adopted by [34].

**Figure 10.**Exploration and generalization capabilities of all the studied techniques in the prior state-of-the-art.

${\mathit{W}}_{1}$ | ${\mathit{L}}_{1}$ | ${\mathit{W}}_{2}$ | ${\mathit{L}}_{2}$ | ${\mathit{W}}_{3}$ | ${\mathit{L}}_{3}$ | ${\mathit{W}}_{4}$ | ${\mathit{A}}_{\mathit{d}}$ | ${\mathit{I}}_{\mathit{c}}$ | |
---|---|---|---|---|---|---|---|---|---|

1 | 5.2 | 0.13 | 10 | 0.2 | 2.4 | 0.3 | 0.24 | 56 | 2.3 |

2 | 4.1 | 0.18 | 11 | 0.6 | 2.1 | 0.35 | 0.4 | 112 | 4 |

… | … | … | … | … | … | … | … | … | … |

Starting Point | Generation Technique | Dataset Size | |
---|---|---|---|

[12] | 1 random point | linear sweeps | 1600 |

[13] | 1 expert design | random variation $\pm 30\%$ | 20,000 |

[14] | 1 expert design | random variation $\pm 5\%$ | 9000 |

[15] | existing database | – | 16,600 |

[16] | – | MaxFit software | 10,000 |

[17] | 1 expert design | normal random distribution | 40,000 |

**Table 3.**Complexities in terms of number of neurons for the different NN structures used in prior state-of-the-art.

References | Inputs | Hidden Layers | Output Layer |
---|---|---|---|

[12] | 3 | 24 + 200 | 1 |

[13] | 12 | Missing | 7 |

[14] | 5 | 15 × 1024 | 6 |

[15] | 4 (expanded: 14) | 120, 240, 60 | 8 |

[16] | 6 | 1 × 9 | 12 |

[17] | 5 | 1 × 50 | 9 |

**Table 4.**Prediction error statistics in % per specification in prior state-of-the-art calculated using Equation (1).

[13] | [14] | [15] | [16] | |
---|---|---|---|---|

Power consumption | 14.5 | – | 9.8 | 3.7 |

Gain | 1.1 | 7.2 | 18.2 | 3.7 |

Gain-BW product | 18.1 | 0.1 | 1.3 | 5.9 |

Phase margin | 5.8 | 5.8 | 1.6 | 3.5 |

Common-mode rej. ratio | 3.7 | 1.6 | – | – |

Power-supply rej. ratio | 2.8 | 7.5 | – | – |

Slew rate | 19.1 | – | – | 2.1 |

Average—Std. Dev. | 9.3–7.7 | 4.4–3.4 | 7.7–8 | 3.8–2.5 |

**Table 5.**Comparative summary of supervised and reinforcement learning techniques in the prior state-of-the-art.

[12] | [13] | [14] | [15] | [16] | [17] | [19] | [20] | [21] | |
---|---|---|---|---|---|---|---|---|---|

MLMethod | superv. | superv. | superv. | superv. | superv. | superv. | reinforc. | reinforc. | reinforc. |

Circuit | bandgap reference | 2-stage opamp | 2-stage opamp | volt. combi. diff. opamp | 2-stage opamp | 2-stage opamp | 3-stage opamp | 2-stage opamp-gm | fold.-casc. opamp |

Fabricationtechnology | CMOS missing | CMOS $<1$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS $<1$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS $0.13$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS $0.18$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS $0.18$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS $0.18$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS 45 $\mathrm{n}$$\mathrm{m}$ | CMOS 65 $\mathrm{n}$$\mathrm{m}$ |

Perform.features | 3 | 12 | 5 | 4 (exp. 14) | 6 | 5 | 6 | 4 | 4 |

Designparameters | 1 | 7 | 6 | 8 | 12 | 9 | 17 | 11 | 16 |

NNcomplexity | 24 + 200 + 1 | 100 + 200 + 7 | $15\phantom{\rule{3.33333pt}{0ex}}\times \phantom{\rule{3.33333pt}{0ex}}1024$ + 6 | 120 + 240 + 60 + 8 | $1\phantom{\rule{3.33333pt}{0ex}}\times \phantom{\rule{3.33333pt}{0ex}}9$ + 12 | 50 + 9 | missing | $3\phantom{\rule{3.33333pt}{0ex}}\times \phantom{\rule{3.33333pt}{0ex}}50$ + 11 | 3 hidden layers |

Averageerror (%) | 0.25 | 7.8 | 4.4 | 7.7 | 3.7 | <10 | missing | 3.7 | missing |

Datasetsize | ∼1600 | 20,000 | 9000 | 16,600 | 10,000 | 40,000 | N/A | N/A | N/A |

Generationtime | missing | 28 h | missing | 0 (existing) | 3.6 h | 16 h | N/A | N/A | N/A |

Trainingtime | missing | 19 min | 18 min | 1 h | 1 h | 30 min | 30 h | 1.6 h | missing |

[32] | [33] | [34] | [35] | [36] | [37] | |
---|---|---|---|---|---|---|

Circuit | cascode LNA induc. deg. | fold.-casc. opamp Vth-bias | 2-stage opamp-gm | fold.-casc. opamp Vth-bias | charge-pump and fold.-casc. opamp | rail-to-rail opamp 5th-ord. filter |

Fabricationtechnology | CMOS $0.18$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS $0.13$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS 45 $\mathrm{n}$$\mathrm{m}$ | CMOS $0.13$ $\mathsf{\mu}$$\mathrm{m}$ | CMOS $40/55$ $\mathrm{n}$$\mathrm{m}$ | CMOS $0.18/0.13$ $\mathsf{\mu}$$\mathrm{m}$ |

Perform.features | 6 | 5 (expanded 20) | 3 | 4 | 6/3 | 4/3 |

Designparameters | 10 | 19 | 11 | 19 | 16/13 | 9/8 |

NNcomplexity | 17 + 10 | $1\phantom{\rule{3.33333pt}{0ex}}\times \phantom{\rule{3.33333pt}{0ex}}100$ + 19 | $5\phantom{\rule{3.33333pt}{0ex}}\times \phantom{\rule{3.33333pt}{0ex}}20\phantom{\rule{3.33333pt}{0ex}}+\phantom{\rule{3.33333pt}{0ex}}3$ | missing | (25 + 10 + 13)/(10 + 13) | (8 + 9)/(16 + 3) |

Averageerror (%) | 6.6 | ∼1 | missing | 0.4 | missing | 0.5/0.8 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Mina, R.; Jabbour, C.; Sakr, G.E.
A Review of Machine Learning Techniques in Analog Integrated Circuit Design Automation. *Electronics* **2022**, *11*, 435.
https://doi.org/10.3390/electronics11030435

**AMA Style**

Mina R, Jabbour C, Sakr GE.
A Review of Machine Learning Techniques in Analog Integrated Circuit Design Automation. *Electronics*. 2022; 11(3):435.
https://doi.org/10.3390/electronics11030435

**Chicago/Turabian Style**

Mina, Rayan, Chadi Jabbour, and George E. Sakr.
2022. "A Review of Machine Learning Techniques in Analog Integrated Circuit Design Automation" *Electronics* 11, no. 3: 435.
https://doi.org/10.3390/electronics11030435