Simultaneous inverse design continuous and discrete parameters of nanophotonic structures via back-propagation inverse neural network

Qiu, Cankun; Wu, Xiaohu; Luo, Zhi; Yang, Hu; Wang, Gao; Liu, Ning; Huang, Bo

doi:10.1016/j.optcom.2020.126641

Cited by 29 publications

(28 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main shallow machine learning models are Support Vector Machines (SVM) [ 23 ], boosting models [ 24 ], and maximum entropy models [ 25 ], etc. The emergence of BP algorithms has effectively promoted the development of deep neural network represented by Multi-Layer Perceptron (MLP) [ 26 ]. Compared with shallow machine learning models, deep neural network models are characterized by deep network layers, large number of network model parameters, and strong learning ability, which has triggered a wave of scholars' research in this field.…”

Section: Methodsmentioning

confidence: 99%

Comprehensive Evaluation of the Tendency of Vertical Collusion in Construction Bidding Based on Deep Neural Network

Zhu

Cheng

Guo³

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

To effectively diagnose and monitor the vertical collusion in construction project bidding, this paper developed a comprehensive evaluation model with deep neural network and transfer learning. By this model, the collusion characteristics of bidders, tenderers, and bid evaluation experts were mined from limited data set hidden and collusion tendency was evaluated. Firstly, 18 evaluation indicators were established from literature review, court file summarization, typical case analysis, and expert consultation. Then, a comprehensive evaluation model was developed with the deep neural network and transfer learning. Finally, the model was trained and tested with the collected data set. The test results showed that the developed model achieved 87.3% identification accuracy in collusion tendency evaluation of different subjects.

show abstract

Section: Methodsmentioning

confidence: 99%

Comprehensive Evaluation of the Tendency of Vertical Collusion in Construction Bidding Based on Deep Neural Network

Zhu

Cheng

Guo³

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The tandem inverse architecture was also found to be effective for simultaneously predicting a combination of discrete design parameters (materials indexed by numbering) and continuous structural parameters (thicknesses) displaying a targeted optical spectrum. 124,125 The limitations of the tandem architecture to handle the non-unique response-todesign mapping for systems with low-dimensional design parameters were also discussed in a recent study. 126 Another strategy to resolve this nonuniqueness involves a stand-alone inverse network with design parameters modeled as multimodal distributions rather than discrete values.…”

Section: Inverse Networkmentioning

confidence: 99%

Machine learning-assisted design of material properties

Kadulkar,

Sherman,

Ganesan

et al. 2022

Preprint

View full text Add to dashboard Cite

Designing functional materials requires a deep search through multidimensional spaces for system parameters that yield desirable material properties. For cases where conventional parameter sweeps or trial-and-error sampling are impractical, inverse methods that frame design as a constrained optimization problem present an attractive alternative. However, even efficient algorithms require time-and resource-intensive characterization of material properties many times during optimization, imposing a design bottleneck. Approaches that incorporate machine learning can help address this limitation and accelerate the discovery of materials with targeted properties. Here, we review how to leverage machine learning to reduce dimensionality to effectively explore design space, accelerate property evaluation, and generate unconventional material structures with optimal properties. We also discuss promising future directions, including integration of machine learning into multiple stages of a design algorithm and interpretation of machine learning models to understand how design parameters relate to material properties.

show abstract

“…However, due to the non-unique relationship between the geometry and the spectral transmission, the NN-based inverse design for nano-photonic devices is usually hard to converge [27,28]. To solve the non-uniqueness issue, a tandem architecture consisting of two separated networks, an inverse network (design network) and a fixed forward network (spectrum network), has been recently presented [27][28][29][30][31][32]. Since the forward models in the reported tandem networks are all pre-trained with the input topology structure data sampled from the simulation process, it could potentially form a much larger input domain than those sampled structures used in the pre-training stages.…”

Section: Introductionmentioning

confidence: 99%

Inverse design of a nano-photonic wavelength demultiplexer with a deep neural network approach

Yuan

Song

et al. 2022

Opt. Express

View full text Add to dashboard Cite

In this paper, we propose a pre-trained-combined neural network (PTCN) as a comprehensive solution to the inverse design of an integrated photonic circuit. By utilizing both the initially pre-trained inverse and forward model with a joint training process, our PTCN model shows remarkable tolerance to the quantity and quality of the training data. As a proof of concept demonstration, the inverse design of a wavelength demultiplexer is used to verify the effectiveness of the PTCN model. The correlation coefficient of the prediction by the presented PTCN model remains greater than 0.974 even when the size of training data is decreased to 17%. The experimental results show a good agreement with predictions, and demonstrate a wavelength demultiplexer with an ultra-compact footprint of 2.6×2.6μm 2 , a high transmission efficiency with a transmission loss of -2dB, a low reflection of -10dB, and low crosstalk around -7dB simultaneously.

show abstract

Simultaneous inverse design continuous and discrete parameters of nanophotonic structures via back-propagation inverse neural network

Cited by 29 publications

References 24 publications

Comprehensive Evaluation of the Tendency of Vertical Collusion in Construction Bidding Based on Deep Neural Network

Comprehensive Evaluation of the Tendency of Vertical Collusion in Construction Bidding Based on Deep Neural Network

Machine learning-assisted design of material properties

Inverse design of a nano-photonic wavelength demultiplexer with a deep neural network approach

Contact Info

Product

Resources

About