서브메뉴
검색
Photochemical and Electro-Optic Devices for Neuromorphic Photonics in Silicon
Photochemical and Electro-Optic Devices for Neuromorphic Photonics in Silicon
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152731
- ISBN
- 9798384467960
- DDC
- 620
- 저자명
- Bilodeau, Simon.
- 서명/저자
- Photochemical and Electro-Optic Devices for Neuromorphic Photonics in Silicon
- 발행사항
- [Sl] : Princeton University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 158 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
- 주기사항
- Advisor: Prucnal, Paul R.
- 학위논문주기
- Thesis (Ph.D.)--Princeton University, 2024.
- 초록/해제
- 요약The training and usage of artificial neural networks forms an increasingly large fraction of total compute. Traditional Von-Neumann digital hardware, however, struggles to efficiently emulate neural computation models. Furthermore, it no longer offers guaranteed improve- ments due to the slowdown of Moore's Law. As such, there is renewed interest in developing neuron-like (neuromorphic) hardware. Neuromorphic photonics, the emulation of neural compute using photonic components, is particularly attractive due to the inherent suitability of light for communication. Photonic integrated circuits (PICs), and specifically silicon photonics, promises the manufacturing scale for its realization.This thesis consists of a collection of results related to neuromorphic photonics in silicon. It begins with a short survey of "standard" silicon photonic neurons, explored through a series of software, designs, and packages co-developed as part of this work. It is then followed by the demonstrations of new silicon photonic devices with built-in neuromorphic functionality. The first device presented is a microring resonator weight configured by the photochemical tuning of a photochromic cladding, an example of on-chip analog memory. To our knowledge, this constitutes one of the first demonstration of commercial-grade, backend compatible light molecule deposition enhancing a silicon PIC. We show interesting properties of this all-optical memory for a silicon photonics platform, including nonvolatility, low-loss in the optical C-band, and first-order photokinetics of the photoconversion leading to continuous, bidirectional, scalable actuation. The limitations of this device are also discussed, namely stability and speed. We then carefully show through computation that, operating in the visible band, this device fulfills the "fingerprints" for a generic memristive device. To our knowledge, this is the first "bottom-up" exploration of an optical memristive device. Finally, we discuss another device: a capacitively-driven silicon microring resonator colocated with a capacitive analog memory. Unlike the previous example, this memory is volatile, but offers higher reconfiguration speeds.
- 일반주제명
- Engineering
- 일반주제명
- Optics
- 일반주제명
- Computer engineering
- 일반주제명
- Electrical engineering
- 키워드
- Optical memory
- 기타저자
- Princeton University Electrical and Computer Engineering
- 기본자료저록
- Dissertations Abstracts International. 86-04B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017163613
■00520250211152731
■006m o d
■007cr#unu||||||||
■020 ▼a9798384467960
■035 ▼a(MiAaPQ)AAI31490904
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a620
■1001 ▼aBilodeau, Simon.▼0(orcid)0000-0003-0667-2732
■24510▼aPhotochemical and Electro-Optic Devices for Neuromorphic Photonics in Silicon
■260 ▼a[Sl]▼bPrinceton University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a158 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-04, Section: B.
■500 ▼aAdvisor: Prucnal, Paul R.
■5021 ▼aThesis (Ph.D.)--Princeton University, 2024.
■520 ▼aThe training and usage of artificial neural networks forms an increasingly large fraction of total compute. Traditional Von-Neumann digital hardware, however, struggles to efficiently emulate neural computation models. Furthermore, it no longer offers guaranteed improve- ments due to the slowdown of Moore's Law. As such, there is renewed interest in developing neuron-like (neuromorphic) hardware. Neuromorphic photonics, the emulation of neural compute using photonic components, is particularly attractive due to the inherent suitability of light for communication. Photonic integrated circuits (PICs), and specifically silicon photonics, promises the manufacturing scale for its realization.This thesis consists of a collection of results related to neuromorphic photonics in silicon. It begins with a short survey of "standard" silicon photonic neurons, explored through a series of software, designs, and packages co-developed as part of this work. It is then followed by the demonstrations of new silicon photonic devices with built-in neuromorphic functionality. The first device presented is a microring resonator weight configured by the photochemical tuning of a photochromic cladding, an example of on-chip analog memory. To our knowledge, this constitutes one of the first demonstration of commercial-grade, backend compatible light molecule deposition enhancing a silicon PIC. We show interesting properties of this all-optical memory for a silicon photonics platform, including nonvolatility, low-loss in the optical C-band, and first-order photokinetics of the photoconversion leading to continuous, bidirectional, scalable actuation. The limitations of this device are also discussed, namely stability and speed. We then carefully show through computation that, operating in the visible band, this device fulfills the "fingerprints" for a generic memristive device. To our knowledge, this is the first "bottom-up" exploration of an optical memristive device. Finally, we discuss another device: a capacitively-driven silicon microring resonator colocated with a capacitive analog memory. Unlike the previous example, this memory is volatile, but offers higher reconfiguration speeds.
■590 ▼aSchool code: 0181.
■650 4▼aEngineering
■650 4▼aOptics
■650 4▼aComputer engineering
■650 4▼aElectrical engineering
■653 ▼aNeuromorphic engineering
■653 ▼aOptical memory
■653 ▼aSilicon photonics
■653 ▼aPhotonic integrated circuits
■653 ▼aPhotochromic cladding
■690 ▼a0537
■690 ▼a0752
■690 ▼a0800
■690 ▼a0544
■690 ▼a0464
■71020▼aPrinceton University▼bElectrical and Computer Engineering.
■7730 ▼tDissertations Abstracts International▼g86-04B.
■790 ▼a0181
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163613▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


