Verilog-A compatible recurrent neural network model for transient circuit simulation

Chen, Zaichen; Raginsky, Maxim; Rosenbaum, Elyse

doi:10.1109/epeps.2017.8329743

Cited by 30 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the prior works on NN-based circuit modeling used discrete-time NN models; examples include the feedforward NN (FNN) with inputs from previous time steps [1], nonlinear autoregressive network with exogenous inputs (NARX) [2], [3], [4], [10], and discrete-time recurrent NN (DTRNN) [7], [8], [9], [11]. All of those models account for the inertia (or "memory") possessed by a circuit.…”

Section: A Capabilities and Limitations Of Prior Workmentioning

confidence: 99%

Neural Ordinary Differential Equation Models of Circuits: Capabilities and Pitfalls

Xiong

Yang

Raginsky

et al. 2022

IEEE Trans. Microwave Theory Techn.

Self Cite

View full text Add to dashboard Cite

This work advances the application of neural ordinary differential equations (ODEs) to circuit modeling. Prior works primarily utilized the recurrent neural network (RNN), which is a specific type of neural ODE. In this work, the capability of neural ODEs to represent different types of circuits is studied. Stability conditions are presented, both for neural ODEs in a standalone configuration and for neural ODEs with feedback connections, and practical techniques to impose the stability constraints during training are demonstrated. Based on the theoretical and experimental results, this work provides guidance as to when and how an accurate and stable neural ODE circuit model can be generated.

show abstract

Section: A Capabilities and Limitations Of Prior Workmentioning

confidence: 99%

Neural Ordinary Differential Equation Models of Circuits: Capabilities and Pitfalls

Xiong

Yang

Raginsky

et al. 2022

IEEE Trans. Microwave Theory Techn.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Especially when modeling nonlinear dynamic systems, RNNs, which include feedback paths allowing for the interaction between the input and output samples as shown in Fig. 6, are preferred [5], [6], [16], [17]. To efficiently capture the nonlinear dynamic behavior of the buffer, the previous time samples of the buffer output current and voltage can be taken into account, and the sub-models can be learnt as RNN models:…”

Section: A Buffer Modelingmentioning

confidence: 99%

Modeling of Voltage-Controlled Oscillators Including I/O Behavior Using Augmented Neural Networks

Chalamalasetty

Swaminathan

2019

IEEE Access

View full text Add to dashboard Cite

This paper proposes augmented neural networks (AugNNs) for modeling the behavior of steady-state oscillators in time-domain. Multi-output AugNNs with the corresponding gradient scheme and training methodology are proposed for the modeling of multi-phase oscillators. Using the proposed AugNNs, a novel technique is presented for the modeling of voltage-controlled oscillators (VCOs) including I/O behavior. In the proposed AugNNs, a periodic unit is introduced to capture the relation between the instantaneous frequency and the control signal, and to provide the phase information of the oscillation, which is used to predict the oscillatory output waveforms using feed forward neural networks (FFNN). For the modeling of VCOs including output buffers, an AugNN-based model is proposed, where recurrent neural networks (RNNs) are used to capture the nonlinear dynamic current-voltage relation at the output port. The simulated data of transistor-level oscillator circuit are used to train the proposed model. As a black-box approach, the proposed model protects intellectual property (IP) and can be implemented in Verilog-A. The examples using transistor-level oscillator circuits demonstrate the effectiveness of the proposed model for time-domain analysis.INDEX TERMS Behavioral modeling, voltage-controlled oscillator (VCO), neural network, output buffer, Verilog-A.

show abstract

“…developed a neural-network method to combat nonlinearities in power amplifiers [3]. Chen Z. et al proposed a method for data-driven behavioral modeling of electronic circuits using recurrent neural networks [4].…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network Based Behavioral Model of Nonlinear Circuits

Zhe¹,

Kaba²

2021

JAMP

View full text Add to dashboard Cite

With the rapid growth of complexity and functionality of modern electronic systems, creating precise behavioral models of nonlinear circuits has become an attractive topic. Deep neural networks (DNNs) have been recognized as a powerful tool for nonlinear system modeling. To characterize the behavior of nonlinear circuits, a DNN based modeling approach is proposed in this paper. The procedure is illustrated by modeling a power amplifier (PA), which is a typical nonlinear circuit in electronic systems. The PA model is constructed based on a feedforward neural network with three hidden layers, and then Multisim circuit simulator is applied to generating the raw training data. Training and validation are carried out in Tensorflow deep learning framework. Compared with the commonly used polynomial model, the proposed DNN model exhibits a faster convergence rate and improves the mean squared error by 13 dB. The results demonstrate that the proposed DNN model can accurately depict the input-output characteristics of nonlinear circuits in both training and validation data sets.

show abstract

Verilog-A compatible recurrent neural network model for transient circuit simulation

Cited by 30 publications

References 0 publications

Neural Ordinary Differential Equation Models of Circuits: Capabilities and Pitfalls

Neural Ordinary Differential Equation Models of Circuits: Capabilities and Pitfalls

Modeling of Voltage-Controlled Oscillators Including I/O Behavior Using Augmented Neural Networks

Deep Neural Network Based Behavioral Model of Nonlinear Circuits

Contact Info

Product

Resources

About