Composable and Reusable Neural Surrogates to Predict System Response of Causal Model Components

    •  Anantharaman, R., Abdelrahim, A., Martinuzzi, F., Yalburgi, S., Saba, E., Fischer, K., Hertz, G., de Vos, P., Laughman, C.R., Ma, Y., Shah, V., Edelman, A., Rackauckas, C., "Composable and Reusable Neural Surrogates to Predict System Response of Causal Model Components", AAAI 2022 Workshop on AI based Design and Manufacturing, March 2022.
      BibTeX TR2022-034 PDF
      • @inproceedings{Anantharaman2022mar,
      • author = {Anantharaman, Ranjan and Abdelrahim, Anas and Martinuzzi, Francesco and Yalburgi, Sharan and Saba, Elliot and Fischer, Keno and Hertz, Glen and de Vos, Pepijn and Laughman, Christopher R. and Ma, Yingbo and Shah, Viral and Edelman, Alan and Rackauckas, Chris},
      • title = {Composable and Reusable Neural Surrogates to Predict System Response of Causal Model Components},
      • booktitle = {AAAI 2022 Workshop on AI based Design and Manufacturing},
      • year = 2022,
      • month = mar,
      • url = {}
      • }
  • MERL Contact:
  • Research Areas:

    Machine Learning, Multi-Physical Modeling, Optimization


Surrogate models, or machine learning based emulators of simulators, have been shown to be a powerful tool for accelerating simulations. However, capturing the system response of general nonlinear systems is still an open area of investigation. In this paper we propose a new surrogate architecture which is capable of capturing the input/output response of causal models to automatically replace large aspects of block model diagrams with neural-accelerated forms. We denote this technique the Nonlinear Response ContinuousTime Echo State Network (NR-CTESN) and describe a training mechanism for it to accurately predict the simulation response to exogenous inputs. We then describe a scienceguided or physics-informed surrogate architecture based on
Cellular Neural Networks to enable the NR-CTESN to accurately reproduce discontinuous output signals. We demonstrate this architecture on an inverter circuit and a Sky130
Digital to Analog Converter (DAC), showcasing a 9x and
300x acceleration of the respective simulations. These results showcase that the NR-CTESN can learn emulate the behavior of components within composable modeling frameworks and thus be reused in new applications without requiring retraining. Together this showcases a machine learning technique that can be used to generate nonlinear model order reductions of model components in SPICE simulators,
Functional Markup Interface (FMI) representations of causal model components, and beyond.