Composable generation strategy framework enabled bidirectional design on topological circuits

被引:0
|
作者
Chen, Xi [1 ]
Sun, Jinyang [2 ]
Wang, Xiumei [3 ]
Chen, Maoxin [2 ]
Lin, Qingyuan [1 ]
Xia, Minggang [4 ]
Zhou, Xingping [5 ]
机构
[1] Nanjing Univ Posts & Telecommun, Coll Integrated Circuit Sci & Engn, Nanjing 210003, Peoples R China
[2] Nanjing Univ Posts & Telecommun, Portland Inst, Nanjing 210003, Peoples R China
[3] Nanjing Univ Posts & Telecommun, Coll Elect & Opt Engn, Nanjing 210003, Peoples R China
[4] Xi An Jiao Tong Univ, Sch Phys, Dept Appl Phys, Xian, Peoples R China
[5] Nanjing Univ Posts & Telecommun, Inst Quantum Informat & Technol, Nanjing 210003, Peoples R China
关键词
REALIZATION;
D O I
10.1103/PhysRevB.110.134108
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Topological insulators show important properties, such as topological phase transitions and topological edge states. Although these properties and phenomena can be simulated by well-designed circuits, it remains a complex task to design such topological circuits due to the intricate physical principles and calculations involved. Therefore, achieving a framework that can automatically complete bidirectional design of topological circuits is very significant. Here, we propose an effective bidirectional collaborative design framework with strong task adaptability, which can automatically perceive inputs and generate outputs in arbitrary combinations of text and images. In the framework, a large language model (LLM) is connected to multimodal and different encoders, which involves building a shared multimodal space by bridging alignment in the diffusion process. For simplicity, a series of two-dimensional Su-Schrieffer-Heeger circuits is constructed with different structural parameters. The framework at first is applied to find the relationship between the structural information and topological features. Then the correctness of the results through experimental measurements can be verified by the automatically generated circuit diagram following the manufacture of a printed circuit board. The framework achieves good results in the reverse design of circuit structures and forward prediction of topological edge states, reaching an accuracy of 94%. The key feature of our framework is its ability to effectively learn the bidirectional mapping between circuit structure and topological impedance response across the spectrum. While recently LLMs have made exciting strides, as humans always communicate through various modalities, developing a framework capable of accepting and delivering content in more modalities becomes essential to human-level artificial intelligence. Overall, in this paper, we demonstrate the enormous potential of the proposed bidirectional deep learning framework in complex tasks and provide insights for collaborative design tasks.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Computational design of synthetic gene circuits with composable parts
    Marchisio, M. A.
    Stelling, J.
    BIOINFORMATICS, 2008, 24 (17) : 1903 - 1910
  • [2] Design and implementation of a composable reflective middleware framework
    Venkatasubramanian, N
    Deshpande, M
    Mohapatra, S
    Gutierrez-Nolasco, SG
    Wickramasuriya, J
    21ST INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS, PROCEEDINGS, 2001, : 644 - 653
  • [3] Generic Hardware Private Circuits Towards Automated Generation of Composable Secure Gadgets
    Knichel D.
    Sasdrich P.
    Moradi A.
    1600, Ruhr-University of Bochum (2022): : 323 - 344
  • [4] Topological Approach to the Design of Terahertz Circuits
    Bahari, B.
    Kante, B.
    2017 IEEE INTERNATIONAL SYMPOSIUM ON ANTENNAS AND PROPAGATION & USNC/URSI NATIONAL RADIO SCIENCE MEETING, 2017, : 61 - 62
  • [5] TOPOLOGICAL GENERATION AND ANALYSIS OF VOLTAGE MULTIPLIER CIRCUITS
    LIN, PM
    CHUA, LO
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1977, 24 (10): : 517 - 530
  • [6] A Composable Design Space Exploration Framework to Optimize Behavioral Locking
    Collini, Luca
    Karri, Ramesh
    Pilato, Christian
    PROCEEDINGS OF THE 2022 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2022), 2022, : 1359 - 1364
  • [7] A NEW APPROACH TO THE TOPOLOGICAL DESIGN OF HYBRID CIRCUITS
    ULBRICH, W
    VANDERLEEDEN, R
    ELECTROCOMPONENT SCIENCE AND TECHNOLOGY, 1980, 7 (1-3): : 181 - 186
  • [8] AUTOMATED TOPOLOGICAL GENERATION AND ANALYSIS OF VOLTAGE MULTIPLIER CIRCUITS
    TAM, KS
    BLOODWORTH, E
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1990, 37 (03): : 432 - 436
  • [9] TOPOLOGICAL GENERATION AND ANALYSIS OF VOLTAGE MULTIPLIER CIRCUITS.
    Lin, P.M.
    Chua, L.O.
    Proceedings - IEEE International Symposium on Circuits and Systems, 1977, : 269 - 272
  • [10] Deep learning-enabled framework for automatic lens design starting point generation
    Cote, Geoffroi
    Lalonde, Jean-Francois
    Thibault, Simon
    OPTICS EXPRESS, 2021, 29 (03) : 3841 - 3854