Alert button
Picture for Slawomir Koziel

Slawomir Koziel

Alert button

Modeling Scattering Coefficients using Self-Attentive Complex Polynomials with Image-based Representation

Jan 10, 2023
Andrew Cohen, Weiping Dou, Jiang Zhu, Slawomir Koziel, Peter Renner, Jan-Ove Mattsson, Xiaomeng Yang, Beidi Chen, Kevin Stone, Yuandong Tian

Figure 1 for Modeling Scattering Coefficients using Self-Attentive Complex Polynomials with Image-based Representation
Figure 2 for Modeling Scattering Coefficients using Self-Attentive Complex Polynomials with Image-based Representation
Figure 3 for Modeling Scattering Coefficients using Self-Attentive Complex Polynomials with Image-based Representation
Figure 4 for Modeling Scattering Coefficients using Self-Attentive Complex Polynomials with Image-based Representation

Finding antenna designs that satisfy frequency requirements and are also optimal with respect to multiple physical criteria is a critical component in designing next generation hardware. However, such a process is non-trivial because the objective function is typically highly nonlinear and sensitive to subtle design change. Moreover, the objective to be optimized often involves electromagnetic (EM) simulations, which is slow and expensive with commercial simulation software. In this work, we propose a sample-efficient and accurate surrogate model, named CZP (Constant Zeros Poles), to directly estimate the scattering coefficients in the frequency domain of a given 2D planar antenna design, without using a simulator. CZP achieves this by predicting the complex zeros and poles for the frequency response of scattering coefficients, which we have theoretically justified for any linear PDE, including Maxwell's equations. Moreover, instead of using low-dimensional representations, CZP leverages a novel image-based representation for antenna topology inspired by the existing mesh-based EM simulation techniques, and attention-based neural network architectures. We demonstrate experimentally that CZP not only outperforms baselines in terms of test loss, but also is able to find 2D antenna designs verifiable by commercial software with only 40k training samples, when coupling with advanced sequential search techniques like reinforcement learning.

Viaarxiv icon

Computational Optimization, Modelling and Simulation: Recent Trends and Challenges

Apr 02, 2014
Xin-She Yang, Slawomir Koziel, Leifur Leifsson

Modelling, simulation and optimization form an integrated part of modern design practice in engineering and industry. Tremendous progress has been observed for all three components over the last few decades. However, many challenging issues remain unresolved, and the current trends tend to use nature-inspired algorithms and surrogate-based techniques for modelling and optimization. This 4th workshop on Computational Optimization, Modelling and Simulation (COMS 2013) at ICCS 2013 will further summarize the latest developments of optimization and modelling and their applications in science, engineering and industry. In this review paper, we will analyse the recent trends in modelling and optimization, and their associated challenges. We will discuss important topics for further research, including parameter-tuning, large-scale problems, and the gaps between theory and applications.

* X. S. Yang, S. Koziel, L. Leifsson, Computational Optimization, Modelling and Simulation: Recent Trends and Challenges, Procedia Computer Science, vol. 18, pp. 855-860 (2013)  
Viaarxiv icon