Circuit Connectivity Inspired Neural Network for Analog Mixed-Signal Functional Modeling

Hassanpourghadi, Mohsen; Su, Stephen Y. H.; Rasul, Rezwan A; Liu, Juzheng; Zhang, Qiaochu; Chen, Mike Shuo-Wei

doi:10.1109/dac18074.2021.9586236

Cited by 11 publications

(19 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way to address this issue has been to impose domain specific inductive biases on model architectures. For example, [14] proposes breaking the circuit into sub-circuits and modeling each with a separate NN in an auto-regressive fashion. However, it requires ad-hoc human input on the definition of sub-circuits.…”

Section: Related Workmentioning

confidence: 99%

“…The main obstacle for large-scale adoption of ML-based methods to circuit design is the difficulty in creating large datasets partly due to expensive simulation run-times. For example the simulation of one instance of a digital to analog converter (DAC) in [14] could take ∼ 30 minutes and this time can become as much as a few days for more complicated circuits. To mitigate this issue, prior work has explored applying adaptive sampling methods such as reinforcement learning [8], bayesian optimization [15], [16], and evolutionary algorithms [9] for optimization of circuits.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design

Hakhamaneshi¹,

Nassar²,

Abbeel³

et al. 2022

Preprint

View full text Add to dashboard Cite

Being able to predict the performance of circuits without running expensive simulations is a desired capability that can catalyze automated design. In this paper, we present a supervised pretraining approach to learn circuit representations that can be adapted to new circuit topologies or unseen prediction tasks. We hypothesize that if we train a neural network (NN) that can predict the output DC voltages of a wide range of circuit instances it will be forced to learn generalizable knowledge about the role of each circuit element and how they interact with each other. The dataset for this supervised learning objective can be easily collected at scale since the required DC simulation to get ground truth labels is relatively cheap. This representation would then be helpful for few-shot generalization to unseen circuit metrics that require more time consuming simulations for obtaining the ground-truth labels. To cope with the variable topological structure of different circuits we describe each circuit as a graph and use graph neural networks (GNNs) to learn node embeddings. We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties with up to 10x more sample efficiency compared to a randomly initialized model. We further show that we can improve sample efficiency of prior SoTA model-based optimization methods by 2x (almost as good as using an oracle model) via fintuning pretrained GNNs as the feature extractor of the learned models.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design

Hakhamaneshi¹,

Nassar²,

Abbeel³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…simulation-and model-based, which both need a circuit modeling tool. In the simulation-based approaches, the circuit modeling tool is invoked multiple times to evaluate the circuit and generate new parameter candidates to meet the desired specifications [2]. In addition, the modeling tool is used to generate the training set of the model-based approaches.…”

Section: Introductionmentioning

confidence: 99%

“…Despite all these advances in functional modeling of circuits, current works [2], [5]- [7], [13]- [17] train directly from circuit design parameters (capacitance value of capacitors, size of transistors, etc.) to Performance of Interests (PoI).…”

Section: Introductionmentioning

confidence: 99%

“…We use the Circuit-Connectivity-Inspired-NN (CCI-NN) structure [2] in our main model to further reduce the number of training sets for each topology. As stated by Hassanpourghadi et al [2], CCI-NN structure requires less training data in comparison with the Fully-Connected NNs (FC-NNs). Moreover, by condensing the design parameters using Sparameters, we may have a smaller design space than the conventional approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AnGeL: Fully-Automated Analog Circuit Generator Using a Neural Network Assisted Semi-Supervised Learning Approach

Fayazi

Taba

Afshari

et al. 2023

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

Automatic synthesis of analog and Radio Frequency (RF) circuits is a trending approach that requires an efficient circuit modeling method. This is due to the expensive cost of running a large number of simulations at each synthesis cycle. Artificial intelligence methods are promising approaches for circuit modeling due to their speed and relative accuracy. However, existing approaches require a large amount of training data, which is still collected using simulation runs. In addition, such approaches collect a whole separate dataset for each circuit topology even if a single element is added or removed. These matters are only exacerbated by the need for post-layout modeling simulations, which take even longer. To alleviate these drawbacks, in this paper, we present FuNToM, a functional modeling method for RF circuits. FuNToM leverages the two-port analysis method for modeling multiple topologies using a single main dataset and multiple small datasets. It also leverages neural networks which have shown promising results in predicting the behavior of circuits. Our results show that for multiple RF circuits, in comparison to the state-of-the-art works, while maintaining the same accuracy, the required training data is reduced by 2.8x -10.9x. In addition, FuNToM needs 176.8x -188.6x less time for collecting the training set in post-layout modeling.

show abstract

Machine learning driven global optimisation framework for analog circuit design

Rashid,

Krishna,

George

et al. 2024

Microelectronics Journal

View full text Add to dashboard Cite

Circuit Connectivity Inspired Neural Network for Analog Mixed-Signal Functional Modeling

Cited by 11 publications

References 12 publications

Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design

Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design

AnGeL: Fully-Automated Analog Circuit Generator Using a Neural Network Assisted Semi-Supervised Learning Approach

Machine learning driven global optimisation framework for analog circuit design

Contact Info

Product

Resources

About