4.6 Article

OptiDistillNet: Learning nonlinear pulse propagation using the student-teacher model

Related references

Note: Only part of the references are listed.
Review Optics

Machine learning and applications in ultrafast photonics

Goery Genty et al.

Summary: The field of smart photonics has seen rapid growth and development in recent years, with machine-learning algorithms being used to enhance optical systems and add new functionalities. Machine learning in ultrafast photonics has shown potential in accelerating technology, particularly in areas such as pulsed laser design, operation, and ultrafast propagation dynamics. However, challenges and future research areas in this field still need to be addressed.

NATURE PHOTONICS (2021)

Article Engineering, Electrical & Electronic

Fast and Accurate Optical Fiber Channel Modeling Using Generative Adversarial Network

Hang Yang et al.

Summary: A new data-driven fiber channel modeling method using generative adversarial network (GAN) is explored in this work. By modifying the loss function, designing the condition vector of input, and addressing mode collapse, GAN successfully learns the distribution of fiber channel transfer function. The method shows remarkable reduction in complexity compared to traditional methods like SSFM, with faster running time and strong generalization abilities.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2021)

Article Computer Science, Artificial Intelligence

Knowledge Distillation: A Survey

Jianping Gou et al.

Summary: This paper provides a comprehensive survey of knowledge distillation, covering knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison, and applications. It also briefly reviews challenges in knowledge distillation and discusses future research directions.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2021)

Article Engineering, Electrical & Electronic

Comparative study of neural network architectures for modelling nonlinear optical pulse propagation

Naveenta Gautam et al.

Summary: This study explores the application of machine learning in diagnosing and reconstructing ultrashort pulses, demonstrating the capability of various neural network architectures in handling the nonlinear Schrödinger equation. By comparing different models, it is shown that a fully connected neural network outperforms others in these tasks.

OPTICAL FIBER TECHNOLOGY (2021)

Article Optics

Artificial neural networks for nonlinear pulse shaping in optical fibers

Sonia Boscolo et al.

OPTICS AND LASER TECHNOLOGY (2020)

Article Multidisciplinary Sciences

Double-slit photoelectron interference in strong-field ionization of the neon dimer

Maksim Kunitski et al.

NATURE COMMUNICATIONS (2019)

Review Computer Science, Information Systems

Harnessing machine learning for fiber-induced nonlinearity mitigation in long-haul coherent optical OFDM

Elias Giacoumidis et al.

FUTURE INTERNET (2019)

Article Optics

Deep learning reconstruction of ultrashort pulses

Tom Zahavy et al.

OPTICA (2018)

Article Engineering, Electrical & Electronic

Nonlinear sculpturing of optical pulses with normally dispersive fiber-based devices

Christophe Finot et al.

OPTICAL FIBER TECHNOLOGY (2018)

Article Multidisciplinary Sciences

Machine learning analysis of extreme events in optical fibre modulation instability

Mikko Narhi et al.

NATURE COMMUNICATIONS (2018)

Review Radiology, Nuclear Medicine & Medical Imaging

Convolutional neural networks: an overview and application in radiology

Rikiya Yamashita et al.

INSIGHTS INTO IMAGING (2018)

Article Engineering, Electrical & Electronic

Ultrafast High-Repetition-Rate Waveguide Lasers

David P. Shepherd et al.

IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS (2016)