Design, fabrication, and metrology of 10 × 100 multi-planar integrated photonic routing manifolds for neural networks

Chiles, Jeff; Buckley, Sonia; Nam, Sae Woo; Mirin, Richard P.; Shainline, Jeffrey M.

doi:10.1063/1.5039641

Cited by 51 publications

(27 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The huge success of deep learning in modeling complex input-output relationship has attracted attention from several scientific communities such as material discovery 15 , high energy physics 16 , single molecule imaging medical diagnosis 17 , and particle physics 18 . It has received some attention in optical community and there has been several recent work on reverse modeling for design of nano-structured optical components using DNN 19–25 , as well as hardware implementation of an artificial neural network 26–30 . NNs can be used to predict the optical response of a topology (Forward Design) as well as to design a topology for a target optical response (Inverse Design).…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network Inverse Design of Integrated Photonic Power Splitters

Tahersima

Kojima

Koike‐Akino

et al. 2019

Sci Rep

306

140

View full text Add to dashboard Cite

Predicting physical response of an artificially structured material is of particular interest for scientific and engineering applications. Here we use deep learning to predict optical response of artificially engineered nanophotonic devices. In addition to predicting forward approximation of transmission response for any given topology, this approach allows us to inversely approximate designs for a targeted optical response. Our Deep Neural Network (DNN) could design compact (2.6 × 2.6 μm2) silicon-on-insulator (SOI)-based 1 × 2 power splitters with various target splitting ratios in a fraction of a second. This model is trained to minimize the reflection (to smaller than ~ −20 dB) while achieving maximum transmission efficiency above 90% and target splitting specifications. This approach paves the way for rapid design of integrated photonic components relying on complex nanostructures.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Neural Network Inverse Design of Integrated Photonic Power Splitters

Tahersima

Kojima

Koike‐Akino

et al. 2019

Sci Rep

306

140

View full text Add to dashboard Cite

show abstract

“…An optical interference unit (OIU) can be realised using various integrated photonics architectures to implement matrices multiplication for weighting and summation. The physical implementation can be classified as optical modes realisation such as linear operation nanophotonics circuits 10,[26][27][28][29] , or multiwavelength realisation such as parallel weighting of optical carrier signals generated from wavelength-division multiplexing using microring resonators weight banks [30][31][32][33][34] . Those have been demonstrated previously during different computational tasks.…”

Section: Nanophotonic Neural Network Mechanism Of Operationmentioning

confidence: 99%

Ti3C2Tx MXene Enabled All-Optical Nonlinear Activation Function for On-Chip Photonic Deep Neural Networks

Hazan

Ratzker

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Neural networks are one of the first major milestones in developing artificial intelligence systems. The utilisation of integrated photonics in neural networks offers a promising alternative approach to microelectronic and hybrid optical-electronic implementations due to improvements in computational speed and low energy consumption in machine-learning tasks. However, at present, most of the neural network hardware systems are still electronic-based due to a lack of optical realisation of the nonlinear activation function. Here, we experimentally demonstrate two novel approaches for implementing an all-optical neural nonlinear activation function based on utilising unique light-matter interactions in 2D Ti3C2Tx (MXene) in the infrared (IR) range in two configurations: 1) a saturable absorber made of MXene thin film, and 2) a silicon waveguide with MXene flakes overlayer. These configurations may serve as nonlinear units in photonic neural networks, while their nonlinear transfer function can be flexibly designed to optimise the performance of different neuromorphic tasks, depending on the operating wavelength. The proposed configurations are reconfigurable and can therefore be adjusted for various applications without the need to modify the physical structure. We confirm the capability and feasibility of the obtained results in machine-learning applications via an Modified National Institute of Standards and Technology (MNIST) handwritten digit classifications task, with near 99% accuracy. Our developed concept for an all-optical neuron is expected to constitute a major step towards the realization of all-optically implemented deep neural networks.

show abstract

“…Neurons in a physical system without charge-based parasitics can achieve direct fan-out to thousands of synaptic connections, avoiding the need for time-multiplexing necessitated by shared communication lines. By using photons rather than electrons for communication across multi-planar routing structures [42], [43], 10-to-100 routing manifolds have been demonstrated [44], and direct fan-out to thousands of connections appears straightforward. By utilizing optical fibers and free-space links in addition to on-chip routing networks, signaling across large-scale, multi-modular cognitive systems may be achieved.…”

Section: Hardware: Electrical and Optical Systemsmentioning

confidence: 99%

The Largest Cognitive Systems Will be Optoelectronic

Shainline

2018

2018 IEEE International Conference on Rebooting Computing (ICRC)

Self Cite

View full text Add to dashboard Cite

Electrons and photons offer complimentary strengths for information processing. Photons are excellent for communication, while electrons are superior for computation and memory. Cognition requires distributed computation to be communicated across the system for information integration. We present reasoning from neuroscience, network theory, and device physics supporting the conjecture that large-scale cognitive systems will benefit from electronic devices performing synaptic, dendritic, and neuronal information processing operating in conjunction with photonic communication. On the chip scale, integrated dielectric waveguides enable fan-out to thousands of connections. On the system scale, fiber and free-space optics can be employed. The largest cognitive systems will be limited by the distance light can travel during the period of a network oscillation. We calculate that optoelectronic networks the area of a large data center (10 5 m 2 ) will be capable of system-wide information integration at 1 MHz. At frequencies of cortex-wide integration in the human brain (4 Hz, theta band), optoelectronic systems could integrate information across the surface of the earth.

show abstract

Design, fabrication, and metrology of 10 × 100 multi-planar integrated photonic routing manifolds for neural networks

Cited by 51 publications

References 24 publications

Deep Neural Network Inverse Design of Integrated Photonic Power Splitters

Deep Neural Network Inverse Design of Integrated Photonic Power Splitters

Ti3C2Tx MXene Enabled All-Optical Nonlinear Activation Function for On-Chip Photonic Deep Neural Networks

The Largest Cognitive Systems Will be Optoelectronic

Contact Info

Product

Resources

About