東華大學圖書館 |

Dynamics and Operations of Photonic Neurons.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Dynamics and Operations of Photonic Neurons./
作者:	Nahmias, Mitchell Aaron.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
面頁冊數:	290 p.
附註:	Source: Dissertations Abstracts International, Volume: 81-06, Section: B.
Contained By:	Dissertations Abstracts International81-06B.
標題:	Optics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27542620
ISBN:	9781392878118

Dynamics and Operations of Photonic Neurons.
Nahmias, Mitchell Aaron.

Dynamics and Operations of Photonic Neurons. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 290 p.

Source: Dissertations Abstracts International, Volume: 81-06, Section: B.

Thesis (Ph.D.)--Princeton University, 2019.

This item must not be sold to any third party vendors.

Photonic communication channels-which code information on lightwaves, rather than electrons-compose both the vast networks that underlie the internet and the fiber links that connect servers at datacenters. Electronics, in contrast, has dominated information processing: digital logic gates, especially those based on complementary metal oxide semiconductor (CMOS) technology, has driven the computing landscape for nearly sixty years with a Moore's law progression towards faster, higher throughput processors. Electronic computing, however, is running up against fundamental physical limitations that are increasingly harder to circumvent.The first major limitation is data movement. More than sixty percent of both the energy and area costs in electronic hardware result from interconnects: the energy lost from capacitively charging and discharging the wires that move information from one point to another. This cost is exacerbated in highly parallel processing models such as field programmable gate arrays (FPGAs), for example, which sometimes have greater than ninety percent of the space or energy costs in the interconnects alone.The second is in data processing. High performance computing (HPC), which involves large-scale simulations of physical phenomena (i.e., weather), solutions to complex systems problems (i.e., social networks), and artificial intelligence (i.e., deep learning), is rapidly becoming a cornerstone in data industries and many fields of science. It is primarily bottlenecked by linear operations such as matrix multiplications and fourier transforms. The demand for deep learning training, for example, appears to be doubling every 3.5 months, far outpacing Moore's law typical progression of transistor density doubling performance every 18 months. This enormous gap between supply and demand presents a significant opportunity for unconventional approaches.Decades ago, photonic computing was unable to match the performance scaling of digital electronics, but today, the landscape has changed tremendously. Moore's law scaling is slowing down at a time when computing demand is expanding more than ever. Scaling technologies now exist for photonics-for example, it is now possible to integrate high efficiency photonic components directly into modern microelectronic chips with only several modifications to the fabrication processes. The energy efficiency (per bit) of optical links are beginning to match or exceed those of electronic chip-to-chip interconnects (< 1 pJ/bit). Further developments in both photonic scalability and miniaturization is expected to lead to better performance as the technology matures.Photonics has the potential to directly address many well-known bottlenecks in electronic computing. For example, an optical communication link only requires charging or discharging optoelectronic transducers, and optical multiplexing allows for enormous on-chip bandwidth capabilities between interacting processors with an energy cost that is nearly constant with respect to the length of the data link. A second useful property is the ability of optical systems to perform linear operations efficiently: a matrix multiplication with N channels will in total perform N2 matrix operations, but the energy required to do this in a passive system scales only with the number of channels N.Motivated by these many advantages, our group has spearheaded a field now known as neuromorphic photonics, in which neural network models are directly instantiated with photonic components. This thesis focuses on the neurons themselves, designed to combine the best properties of electronic and photonic signals while remaining compatible with photonic integrated circuit (PIC) platforms to assure future scalability and compatibility. We discuss several neuromorphic photonic units: the first model is a fully functional laser neuron in a photonic integrated circuit platform: it involves an integrated laser driven by a photodetector through a short, recieverless electronic link, exhibiting biologically-relevant spiking behavior at a sub-nanosecond timing resolution. We also discuss new models based on modulator-class systems, together with the use of novel materials (graphene) or nonlinear effects (the quantum confined stark effect). We end with a detailed comparison of neural network-inspired photonic integrated circuits with current systems in digital and analog electronics, showing significant advantages in the photonic domain for matrix-like operations in artificial intelligence.

ISBN: 9781392878118Subjects--Topical Terms:

517925
Optics.
Subjects--Index Terms:

Artificial intelligence

Dynamics and Operations of Photonic Neurons.
LDR:05702nmm a2200385 4500 001 2272874
005 20201105110247.5
008 220629s2019 ||||||||||||||||| ||eng d
020 $a 9781392878118
035 $a (MiAaPQ)AAI27542620
035 $a AAI27542620
040 $a MiAaPQ $c MiAaPQ
100 1 $a Nahmias, Mitchell Aaron. $3 3550298
245 1 0 $a Dynamics and Operations of Photonic Neurons.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 290 p.
500 $a Source: Dissertations Abstracts International, Volume: 81-06, Section: B.
500 $a Advisor: Prucnal, Paul.
502 $a Thesis (Ph.D.)--Princeton University, 2019.
506 $a This item must not be sold to any third party vendors.
520 $a Photonic communication channels-which code information on lightwaves, rather than electrons-compose both the vast networks that underlie the internet and the fiber links that connect servers at datacenters. Electronics, in contrast, has dominated information processing: digital logic gates, especially those based on complementary metal oxide semiconductor (CMOS) technology, has driven the computing landscape for nearly sixty years with a Moore's law progression towards faster, higher throughput processors. Electronic computing, however, is running up against fundamental physical limitations that are increasingly harder to circumvent.The first major limitation is data movement. More than sixty percent of both the energy and area costs in electronic hardware result from interconnects: the energy lost from capacitively charging and discharging the wires that move information from one point to another. This cost is exacerbated in highly parallel processing models such as field programmable gate arrays (FPGAs), for example, which sometimes have greater than ninety percent of the space or energy costs in the interconnects alone.The second is in data processing. High performance computing (HPC), which involves large-scale simulations of physical phenomena (i.e., weather), solutions to complex systems problems (i.e., social networks), and artificial intelligence (i.e., deep learning), is rapidly becoming a cornerstone in data industries and many fields of science. It is primarily bottlenecked by linear operations such as matrix multiplications and fourier transforms. The demand for deep learning training, for example, appears to be doubling every 3.5 months, far outpacing Moore's law typical progression of transistor density doubling performance every 18 months. This enormous gap between supply and demand presents a significant opportunity for unconventional approaches.Decades ago, photonic computing was unable to match the performance scaling of digital electronics, but today, the landscape has changed tremendously. Moore's law scaling is slowing down at a time when computing demand is expanding more than ever. Scaling technologies now exist for photonics-for example, it is now possible to integrate high efficiency photonic components directly into modern microelectronic chips with only several modifications to the fabrication processes. The energy efficiency (per bit) of optical links are beginning to match or exceed those of electronic chip-to-chip interconnects (< 1 pJ/bit). Further developments in both photonic scalability and miniaturization is expected to lead to better performance as the technology matures.Photonics has the potential to directly address many well-known bottlenecks in electronic computing. For example, an optical communication link only requires charging or discharging optoelectronic transducers, and optical multiplexing allows for enormous on-chip bandwidth capabilities between interacting processors with an energy cost that is nearly constant with respect to the length of the data link. A second useful property is the ability of optical systems to perform linear operations efficiently: a matrix multiplication with N channels will in total perform N2 matrix operations, but the energy required to do this in a passive system scales only with the number of channels N.Motivated by these many advantages, our group has spearheaded a field now known as neuromorphic photonics, in which neural network models are directly instantiated with photonic components. This thesis focuses on the neurons themselves, designed to combine the best properties of electronic and photonic signals while remaining compatible with photonic integrated circuit (PIC) platforms to assure future scalability and compatibility. We discuss several neuromorphic photonic units: the first model is a fully functional laser neuron in a photonic integrated circuit platform: it involves an integrated laser driven by a photodetector through a short, recieverless electronic link, exhibiting biologically-relevant spiking behavior at a sub-nanosecond timing resolution. We also discuss new models based on modulator-class systems, together with the use of novel materials (graphene) or nonlinear effects (the quantum confined stark effect). We end with a detailed comparison of neural network-inspired photonic integrated circuits with current systems in digital and analog electronics, showing significant advantages in the photonic domain for matrix-like operations in artificial intelligence.
590 $a School code: 0181.
650 4 $a Optics. $3 517925
650 4 $a Computational physics. $3 3343998
650 4 $a Artificial intelligence. $3 516317
653 $a Artificial intelligence
653 $a Lasers
653 $a Neural networks
653 $a Neuromorphic photonics
653 $a Photonics
653 $a Unconventional computing
690 $a 0752
690 $a 0216
690 $a 0800
710 2 $a Princeton University. $b Electrical Engineering. $3 2095953
773 0 $t Dissertations Abstracts International $g 81-06B.
790 $a 0181
791 $a Ph.D.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27542620