Artificial Intelligence-Generated Terahertz Multi-Resonant Metasurfaces via Improved Transformer and CGAN Neural Networks

• URL: http://arxiv.org/abs/2307.11794v1
• Date: Fri, 21 Jul 2023 02:49:03 GMT
• Title: Artificial Intelligence-Generated Terahertz Multi-Resonant Metasurfaces via Improved Transformer and CGAN Neural Networks
• Authors: Yangpeng Huang, Naixing Feng, Yijun Cai
• Abstract summary: We propose improved Transformer and conditional generative adversarial neural networks (CGAN) for the inverse design of graphene metasurfaces. The improved Transformer can obtain higher accuracy and generalization performance in the StoV (Spectrum to Vector) spectra. CGAN can achieve the inverse design of graphene metasurface images directly from the desired multi-resonant absorption spectra.
• Score: 2.1592777170316366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is well known that the inverse design of terahertz (THz) multi-resonant graphene metasurfaces by using traditional deep neural networks (DNNs) has limited generalization ability. In this paper, we propose improved Transformer and conditional generative adversarial neural networks (CGAN) for the inverse design of graphene metasurfaces based upon THz multi-resonant absorption spectra. The improved Transformer can obtain higher accuracy and generalization performance in the StoV (Spectrum to Vector) design compared to traditional multilayer perceptron (MLP) neural networks, while the StoI (Spectrum to Image) design achieved through CGAN can provide more comprehensive information and higher accuracy than the StoV design obtained by MLP. Moreover, the improved CGAN can achieve the inverse design of graphene metasurface images directly from the desired multi-resonant absorption spectra. It is turned out that this work can finish facilitating the design process of artificial intelligence-generated metasurfaces (AIGM), and even provide a useful guide for developing complex THz metasurfaces based on 2D materials using generative neural networks.

Related papers

• Anchor-Controlled Generative Adversarial Network for High-Fidelity Electromagnetic and Structurally Diverse Metasurface Design [6.452006201454395]
  We propose Anchor-controlled Generative Adversarial Network (AcGAN) to improve electromagnetic fidelity and structural diversity. AcGAN reduces the Mean Squared Error (MSE) by 73% compared to current state-of-the-art GANs methods.
  arXiv  Detail & Related papers  (2024-08-29T03:11:55Z)
• DeepGate3: Towards Scalable Circuit Representation Learning [9.910071321534682]
  Circuit representation learning has shown promising results in advancing the field of Electronic Design Automation (EDA) Existing models, such as DeepGate Family, primarily utilize Graph Neural Networks (GNNs) to encode circuit netlists into gate-level embeddings. We introduce DeepGate3, an enhanced architecture that integrates Transformer modules following the initial GNN processing.
  arXiv  Detail & Related papers  (2024-07-15T02:44:21Z)
• B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers [97.75725574963197]
  We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training. We show that a sequence of such transformations induces a single linear transformation that faithfully summarises the full model computations. We show that the resulting explanations are of high visual quality and perform well under quantitative interpretability metrics.
  arXiv  Detail & Related papers  (2023-06-19T12:54:28Z)
• NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning [25.197394237526865]
  We propose a modified Transformer-based universal neural network representation learning model NAR-Former V2. Specifically, we take the network as a graph and design a straightforward tokenizer to encode the network into a sequence. We incorporate the inductive representation learning capability of GNN into Transformer, enabling Transformer to generalize better when encountering unseen architecture.
  arXiv  Detail & Related papers  (2023-06-19T09:11:04Z)
• Deep-Learning Empowered Inverse Design for Freeform Reconfigurable Metasurfaces [3.728073286482581]
  We present a deep-learning empowered inverse design method for freeform reconfigurable metasurfaces. A convolutional neural network model is trained to predict the responses of free-shaped meta-atoms. An inverse-designed wideband reconfigurable metasurface prototype is fabricated and measured for beam scanning applications.
  arXiv  Detail & Related papers  (2022-11-11T15:01:32Z)
• Learnable Filters for Geometric Scattering Modules [64.03877398967282]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2022-08-15T22:30:07Z)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)
• Progressive Encoding for Neural Optimization [92.55503085245304]
  We show the competence of the PPE layer for mesh transfer and its advantages compared to contemporary surface mapping techniques. Most importantly, our technique is a parameterization-free method, and thus applicable to a variety of target shape representations.
  arXiv  Detail & Related papers  (2021-04-19T08:22:55Z)
• Data-Driven Learning of Geometric Scattering Networks [74.3283600072357]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2020-10-06T01:20:27Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)
• A Freeform Dielectric Metasurface Modeling Approach Based on Deep Neural Networks [7.039798390237901]
  In this paper, a deep learning-based metasurface/meta-atom modeling approach is introduced to significantly reduce the characterization time. Based on a convolutional neural network (CNN) structure, the proposed deep learning network is able to model meta-atoms with free-form 2D patterns and different lattice sizes. The presented approach features the capability to predict meta-atoms' wide spectrum responses in the timescale of milliseconds.
  arXiv  Detail & Related papers  (2020-01-01T01:21:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.