George Mourgias-Alexandris

Nikolaos Pleros

Neural Comput. Appl., October, 2023

Robust Architecture-Agnostic and Noise Resilient Training of Photonic Deep Learning Models.

[BibT_eX]

[DOI]

George Dabos

IEEE Trans. Emerg. Top. Comput. Intell., February, 2023

Analog Iterative Machine (AIM): using light to solve quadratic optimization problems with mixed variables.

[BibT_eX]

[DOI]

Kirill P. Kalinin

Antony I. T. Rowstron

CoRR, 2023

DDOS attack identification via a silicon photonic Deep Neural Network with 50 GHz input and weight update.

[BibT_eX]

[DOI]

Dimitrios Kalavrouziotis

Dimitris Syrivelis

Paraskevas Bakopoulos

Elad Mentovich

Proceedings of the Optical Fiber Communications Conference and Exhibition, 2023

Quantization-Aware Training for Mixed Precision Photonic Neural Networks.

[BibT_eX]

[DOI]

Nikolaos Pleros

Proceedings of the 33rd IEEE International Workshop on Machine Learning for Signal Processing, 2023

2022

Optical neural networks for deep learning applications

[BibT_eX]

[DOI]

PhD thesis, 2022

Quantization-aware training for low precision photonic neural networks.

[BibT_eX]

[DOI]

Neural Networks, 2022

Normalized Post-training Quantization for Photonic Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium Series on Computational Intelligence, 2022

Photonic Neuromorphic Computing: Architectures, Technologies, and Training Models.

[BibT_eX]

[DOI]

Angelina Totovic

Proceedings of the Optical Fiber Communications Conference and Exhibition, 2022

Learning photonic neural network initialization for noise-aware end-to-end fiber transmission.

[BibT_eX]

[DOI]

Nikos Passalis

George Dabos

Proceedings of the 30th European Signal Processing Conference, 2022

A Robust, Quantization-Aware Training Method for Photonic Neural Networks.

[BibT_eX]

[DOI]

Nikos Passalis

Proceedings of the Engineering Applications of Neural Networks, 2022

2021

Training Deep Photonic Convolutional Neural Networks With Sinusoidal Activations.

[BibT_eX]

[DOI]

IEEE Trans. Emerg. Top. Comput. Intell., 2021

A Silicon Photonic Coherent Neuron with 10GMAC/sec processing line-rate.

[BibT_eX]

[DOI]

Proceedings of the Optical Fiber Communications Conference and Exhibition, 2021

20 Gb/s WDM Optical RAM Row Architecture based on four Monolithic Integrated InP Memory Cells.

[BibT_eX]

[DOI]

Theoni Alexoudi

Konstantinos Fotiadis

Christos Vagionas

Proceedings of the Optical Fiber Communications Conference and Exhibition, 2021

Compute with Light: Architectures, Technologies and Training Models for Neuromorphic Photonic Circuits.

[BibT_eX]

[DOI]

Nikos Passalis

Proceedings of the European Conference on Optical Communication, 2021

25GMAC/sec/axon photonic neural networks with 7GHz bandwidth optics through channel response-aware training.

[BibT_eX]

[DOI]

Proceedings of the European Conference on Optical Communication, 2021

Silicon-integrated coherent neurons with 32GMAC/sec/axon compute line-rates using EAM-based input and weighting cells.

[BibT_eX]

[DOI]

Proceedings of the European Conference on Optical Communication, 2021

2020

Initializing photonic feed-forward neural networks using auxiliary tasks.

[BibT_eX]

[DOI]

Neural Networks, 2020

All-Optical Recurrent Neural Network with Sigmoid Activation Function.

[BibT_eX]

[DOI]

Proceedings of the Optical Fiber Communications Conference and Exhibition, 2020

Adaptive Initialization for Recurrent Photonic Networks using Sigmoidal Activations.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Symposium on Circuits and Systems, 2020

Training Noise-Resilient Recurrent Photonic Networks for Financial Time Series Analysis.

[BibT_eX]

[DOI]

George Dabos

Proceedings of the 28th European Signal Processing Conference, 2020

Time-series classification with an all-optical recurrent neuron.

[BibT_eX]

[DOI]

Proceedings of the European Conference on Optical Communications, 2020

2019

Optics for Disaggregating Data Centers and Disintegrating Computing.

[BibT_eX]

[DOI]

Stelios Pitris

Charoula Mitsolidou

Christos Vagionas

Konstantinos Vyrsokinos

Theoni Alexoudi

Proceedings of the Optical Network Design and Modeling, 2019

Experimental Demonstration of an Optical Neuron with a Logistic Sigmoid Activation Function.

[BibT_eX]

[DOI]

Proceedings of the Optical Fiber Communications Conference and Exhibition, 2019

Variance Preserving Initialization for Training Deep Neuromorphic Photonic Networks with Sinusoidal Activations.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

High-Port and Low-Latency Optical Switches for Disaggregated Data Centers: The Hipoλaos Switch Architecture [Invited].

[BibT_eX]

[DOI]

Theonitsa Alexoudi

K. Vyrsokinos

JOCN, 2018

Optical Thresholding Device with a Sigmoidal Transfer Function.

[BibT_eX]

[DOI]

Theonitsa Alexoudi

Konstantinos Vyrsokinos

Proceedings of the Photonics in Switching and Computing, 2018

A 10Gb/s All-Optical Match-line for optical Content Addressable Memory (CAM) Rows.

[BibT_eX]

[DOI]

Proceedings of the Optical Fiber Communications Conference and Exposition, 2018

Sub-μs Latency High-Port Optical Packet Switch Fabrics for Disaggregated Computing: The Hipoλaos OPS Architecture.

[BibT_eX]

[DOI]

Kostantinos Vyrsokinos

Proceedings of the 2018 20th International Conference on Transparent Optical Networks (ICTON), 2018

A 1024-Port sub-µsee Latency Optical Packet Switch Using the Hipoλaos λ-Routed Modified Spanke Switch Architecture.

[BibT_eX]

[DOI]

Kostantinos Vyrsokinos

Proceedings of the European Conference on Optical Communication, 2018

Multicasting in a 256-Port Sub-#181;sec Latency Hipoλaos Switch Architecture for Disaggregated DataCenters.

[BibT_eX]

[DOI]

Konstantinos Vyrsoklnos