Interpretable Artificial Intelligence for Topological Photonics

Ali Ghorashi; Sachin Vaidya; Ziming Liu; Charlotte Loh; Thomas Christensen; Max Tegmark; Marin Soljacic

doi:10.1364/CLEO_FS.2025.FF138_5

Interpretable Artificial Intelligence for Topological Photonics

Ali Ghorashi, Sachin Vaidya, Ziming Liu, Charlotte Loh, Thomas Christensen, Max Tegmark, Marin Soljacic

Massachusetts Institute of Technology

Research output: Contribution to conference › Conference abstract for conference › Research › peer-review

Abstract

We use sparse neural networks and KANs to obtain interpretable design principles governing band topology in photonic crystals, creating a dataset of photonic crystals with deterministic band topologies below the first gap.

Original language	English
Publication date	2025
Number of pages	2
DOIs	https://doi.org/10.1364/CLEO_FS.2025.FF138_5
Publication status	Published - 2025
Event	CLEO: Conference on Lasers and Electro-Optics 2025 - Long Beach Convention & Entertainment Center, Long Beach, United States Duration: 4 May 2025 → 9 May 2025

Conference

Conference	CLEO: Conference on Lasers and Electro-Optics 2025
Location	Long Beach Convention & Entertainment Center
Country/Territory	United States
City	Long Beach
Period	04/05/2025 → 09/05/2025

Bibliographical note

From the session: Topological and non-Hermitian photonics (paper FF138_5)

Access to Document

10.1364/CLEO_FS.2025.FF138_5

OpenUrl availability

Full text

Cite this

@conference{871f134bfa1849e8a00076c5733a3dfd,

title = "Interpretable Artificial Intelligence for Topological Photonics",

abstract = "We use sparse neural networks and KANs to obtain interpretable design principles governing band topology in photonic crystals, creating a dataset of photonic crystals with deterministic band topologies below the first gap.",

author = "Ali Ghorashi and Sachin Vaidya and Ziming Liu and Charlotte Loh and Thomas Christensen and Max Tegmark and Marin Soljacic",

note = "From the session: Topological and non-Hermitian photonics (paper FF138\_5); CLEO: Conference on Lasers and Electro-Optics 2025 ; Conference date: 04-05-2025 Through 09-05-2025",

year = "2025",

doi = "10.1364/CLEO\_FS.2025.FF138\_5",

language = "English",

pages = "1--2",

}

TY - ABST

T1 - Interpretable Artificial Intelligence for Topological Photonics

AU - Ghorashi, Ali

AU - Vaidya, Sachin

AU - Liu, Ziming

AU - Loh, Charlotte

AU - Christensen, Thomas

AU - Tegmark, Max

AU - Soljacic, Marin

N1 - From the session: Topological and non-Hermitian photonics (paper FF138_5)

PY - 2025

Y1 - 2025

N2 - We use sparse neural networks and KANs to obtain interpretable design principles governing band topology in photonic crystals, creating a dataset of photonic crystals with deterministic band topologies below the first gap.

AB - We use sparse neural networks and KANs to obtain interpretable design principles governing band topology in photonic crystals, creating a dataset of photonic crystals with deterministic band topologies below the first gap.

U2 - 10.1364/CLEO_FS.2025.FF138_5

DO - 10.1364/CLEO_FS.2025.FF138_5

M3 - Conference abstract for conference

SP - 1

EP - 2

T2 - CLEO: Conference on Lasers and Electro-Optics 2025

Y2 - 4 May 2025 through 9 May 2025

ER -

Interpretable Artificial Intelligence for Topological Photonics

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this