VI: Free-Space Optical Digital Computing and Interconnection

Jahns, Jürgen

doi:10.1016/s0079-6638(08)70354-8

Cited by 8 publications

(7 citation statements)

References 151 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since that time, a body of work (see, for example, [4] and [6]- [33]) has addressed potential benefits and limits of optics for interconnection [4], [7], [8], [12], [14]- [16], [20], [23], [24], [28], analysis of the relative benefits of optics versus electronics [4], [6], [9]- [11], [13], [21], [22], [26], [27], [30], [31], [33], and comparison of different kinds of optical approaches against one another [17]- [19], [25], [29]. Several of these papers review parts of this work (e.g., [20], [22], [27], and [28]). …”

Section: A Historical Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Rationale and challenges for optical interconnects to electronic chips

2000

View full text Add to dashboard Cite

Section: A Historical Backgroundmentioning

confidence: 99%

“…Many of these techniques have been recently reviewed in [49]. References [28], [42], and [50]- [59] give examples of free-space systems investigated for optical interconnect applications. Waveguides on silicon chips have been investigated [60]- [62], though complete systems using these are not yet demonstrated.…”

Section: A Historical Backgroundmentioning

confidence: 99%

Rationale and challenges for optical interconnects to electronic chips

2000

View full text Add to dashboard Cite

“…Optics offers large temporal and spatial bandwidth. Much work has been done in this area over the past 20 years [28,29]. Recently, the approach of silicon integrated optics has been pushed forward strongly [30], which implies that all functionality including light emission, propagation and detection are implemented in a monolithic fashion.…”

Section: Microoptical Systemsmentioning

confidence: 99%

Micro‐ and nanooptics – an overview

Jahns¹,

Cao

Sinzinger

2008

Laser & Photonics Reviews

View full text Add to dashboard Cite

Since the 1960s the minimum feature size of lithographic fabrication has shrunk from tens of micrometers to now a few nanometers, i.e. by one order of magnitude per decade. With the adaptation of lithographic techniques to the fabrication of optical elements, first micro-and more recently nanostructured optics was shown to be both feasible and useful. However, the incredibly shrinking feature size down to the scale of the optical wavelength and below does not only represent a quantitative measure, but it stands for qualitatively different optical phenomena that occur in the subwavelength regime. In that regard, micro-and nanooptics are two different worlds. Their common feature, however, is the succession of steps: computer-based design, modeling and simulation, fabrication and technology, characterization and application. We review recent progress in micro-and nanooptics by describing the state-of-the art and by emphasizing specific areas of interest.A photon sieve is a novel diffractive element which consists of many pinholes suitably arranged according to the ring pattern of a Fresnel zone plate (also shown here for instructive purposes). Position, size and density of the pinholes can be used as design parameters.

show abstract

“…In recent decades, significant effort has been invested in developing optical computers for real-time data processing, owing to their potential advantages in terms of speed and parallelism over electronic computers [ 1 , 2 , 3 ]. However, optical computing has not surpassed digital computing due to the faster progress and greater power, ease of use, and flexibility of its competitor [ 4 ].…”

Section: Introductionmentioning

confidence: 99%

Bidirectional Optical Neural Networks Based on Free-Space Optics Using Lens Arrays and Spatial Light Modulator

2024

Micromachines

View full text Add to dashboard Cite

This paper introduces a novel architecture—bidirectional optical neural network (BONN)—for providing backward connections alongside forward connections in artificial neural networks (ANNs). BONN incorporates laser diodes and photodiodes and exploits the properties of Köhler illumination to establish optical channels for backward directions. Thus, it has bidirectional functionality that is crucial for algorithms such as the backpropagation algorithm. BONN has a scaling limit of 96 × 96 for input and output arrays, and a throughput of 8.5 × 1015 MAC/s. While BONN’s throughput may rise with additional layers for continuous input, limitations emerge in the backpropagation algorithm, as its throughput does not scale with layer count. The successful BONN-based implementation of the backpropagation algorithm requires the development of a fast spatial light modulator to accommodate frequent data flow changes. A two-mirror-like BONN and its cascaded extension are alternatives for multilayer emulation, and they help save hardware space and increase the parallel throughput for inference. An investigation into the application of the clustering technique to BONN revealed its potential to help overcome scaling limits and to provide full interconnections for backward directions between doubled input and output ports. BONN’s bidirectional nature holds promise for enhancing supervised learning in ANNs and increasing hardware compactness.

show abstract

VI: Free-Space Optical Digital Computing and Interconnection

Cited by 8 publications

References 151 publications

Rationale and challenges for optical interconnects to electronic chips

Rationale and challenges for optical interconnects to electronic chips

Micro‐ and nanooptics – an overview

Bidirectional Optical Neural Networks Based on Free-Space Optics Using Lens Arrays and Spatial Light Modulator

Contact Info

Product

Resources

About