An Adjoint Variable Method for Wideband Second-Order Sensitivity Analysis Through FDTD

Negm, Mohamed H.; Bakr, Mohamed H.

doi:10.1109/tap.2015.2510373

Cited by 18 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order for backpropagation to be applied, the physical materialization of adjoint variable method (AVM) [ 103 , 104 ] is needed, which allows for the reverse designing of photonic structures. According to this, at first, the adjoint of the initial field is created, the complementary one is propagated in the network reversely to the initial one and the initial field contributes with a replica of the reverse time of the complementary field.…”

Section: Training Methodologiesmentioning

confidence: 99%

A Comprehensive Survey on Nanophotonic Neural Networks: Architectures, Training Methods, Optimization, and Activations Functions

Demertzis

Papadopoulos

Iliadis

et al. 2022

Sensors

View full text Add to dashboard Cite

In the last years, materializations of neuromorphic circuits based on nanophotonic arrangements have been proposed, which contain complete optical circuits, laser, photodetectors, photonic crystals, optical fibers, flat waveguides and other passive optical elements of nanostructured materials, which eliminate the time of simultaneous processing of big groups of data, taking advantage of the quantum perspective, and thus highly increasing the potentials of contemporary intelligent computational systems. This article is an effort to record and study the research that has been conducted concerning the methods of development and materialization of neuromorphic circuits of neural networks of nanophotonic arrangements. In particular, an investigative study of the methods of developing nanophotonic neuromorphic processors, their originality in neuronic architectural structure, their training methods and their optimization was realized along with the study of special issues such as optical activation functions and cost functions. The main contribution of this research work is that it is the first time in the literature that the most well-known architectures, training methods, optimization and activations functions of the nanophotonic networks are presented in a single paper. This study also includes an extensive detailed meta-review analysis of the advantages and disadvantages of nanophotonic networks.

show abstract

Section: Training Methodologiesmentioning

confidence: 99%

A Comprehensive Survey on Nanophotonic Neural Networks: Architectures, Training Methods, Optimization, and Activations Functions

Demertzis

Papadopoulos

Iliadis

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In order for Backpropagation to be applied, the physical materialization of Adjoint Variable Method (AVM) [90], [91] is needed, which allows the reverse designing of photonic structures. According to this, at first, the adjoint of the initial field is created, the complementary one is propagated in the network reversely to the initial one and the initial field contributes with a replica of the reverse time of the complementary field.…”

Section: δ𝑤 =mentioning

confidence: 99%

A Comprehensive Survey on Nanophotonics Neural Networks

Demertzis¹,

Παπαδόπουλος²,

Iliadis³

et al. 2021

Preprint

View full text Add to dashboard Cite

: In the last years, materializations of neuromorphic circuits based on nanophotonic arrangements have been proposed, which contain complete optical circuits, laser, photodetectors, photonic crystals, optical fibers, flat waveguides, and other passive optical elements of nanostructured materials, which eliminate the time of simultaneous processing of big groups of data, taking advantage of the quantum perspective and thus highly increasing the potentials of contemporary intelligent computational systems. This article is an effort to record and study the research that has been conducted concerning the methods of development and materialization of neuromorphic circuits of Neural Networks of nanophotonic arrangements. In particular, an investigative study of the methods of developing nanophotonic neuromorphic processors, their originality in neuronic architectural structure, their training methods and their optimization has been realized along with the study of special issues such as optical activation functions and cost functions.

show abstract

“…In the case of gradient-based algorithms, a considerable speedup can be achieved using the adjoint sensitivity techniques [7,8]. Unfortunately, the adjoint technology is not widely accessible through commercial solvers [9]. An alternative approach is surrogate-based optimisation (SBO) method [10].…”

Section: Introductionmentioning

confidence: 99%

Computationally‐efficient design optimisation of antennas by accelerated gradient search with sensitivity and design change monitoring

Pietrenko‐Dabrowska

Kozieł

2019

IET Microwaves, Antennas & Propagation

View full text Add to dashboard Cite

Electromagnetic (EM) simulation tools are of primary importance in the design of contemporary antennas. The necessity of accurate performance evaluation of complex structures is a reason why the final tuning of antenna dimensions, aimed at improvement of electrical and field characteristics, needs to be based on EM analysis. Design automation is highly desirable and can be achieved by coupling EM solvers with numerical optimisation routines. Unfortunately, its computational overhead may be impractically high for conventional algorithms. This study proposes an efficient gradient search algorithm with numerical derivatives. The acceleration of the optimisation process is obtained by means of the two mechanisms developed to suppress some of finite‐differentiation‐based updates of the antenna response sensitivities that involve monitoring and quantifying the gradient changes as well as design relocation between the consecutive algorithm iterations. Both methods considerably reduce the need for finite differentiation, leading to significant computational savings. At the same time, excellent reliability and repeatability is maintained, which is demonstrated through statistics over multiple algorithm runs with random initial designs. The proposed approach is validated using a benchmark set of wideband antennas. The proposed algorithm is competitive to both the reference trust‐region algorithm as well as its recently reported accelerated versions.

show abstract

An Adjoint Variable Method for Wideband Second-Order Sensitivity Analysis Through FDTD

Cited by 18 publications

References 37 publications

A Comprehensive Survey on Nanophotonic Neural Networks: Architectures, Training Methods, Optimization, and Activations Functions

A Comprehensive Survey on Nanophotonic Neural Networks: Architectures, Training Methods, Optimization, and Activations Functions

A Comprehensive Survey on Nanophotonics Neural Networks

Computationally‐efficient design optimisation of antennas by accelerated gradient search with sensitivity and design change monitoring

Contact Info

Product

Resources

About