Search Results for author: Serge Massar

Found 12 papers, 0 papers with code

Efficient Optimisation of Physical Reservoir Computers using only a Delayed Input

no code implementations25 Jan 2024 Enrico Picco, Lina Jaurigue, Kathy Lüdge, Serge Massar

We present an experimental validation of a recently proposed optimization technique for reservoir computing, using an optoelectronic setup.

Weak Kerr Nonlinearity Boosts the Performance of Frequency-Multiplexed Photonic Extreme Learning Machines: A Multifaceted Approach

no code implementations19 Dec 2023 Marina Zajnulina, Alessandro Lupo, Serge Massar

We provide a theoretical, numerical, and experimental investigation of the Kerr nonlinearity impact on the performance of a frequency-multiplexed Extreme Learning Machine (ELM).

Deep Photonic Reservoir Computer for Speech Recognition

no code implementations11 Dec 2023 Enrico Picco, Alessandro Lupo, Serge Massar

Speech recognition is a critical task in the field of artificial intelligence and has witnessed remarkable advancements thanks to large and complex neural networks, whose training process typically requires massive amounts of labeled data and computationally intensive operations.

speech-recognition Speech Recognition

Random pattern and frequency generation using a photonic reservoir computer with output feedback

no code implementations19 Dec 2020 Piotr Antonik, Michiel Hermans, Marc Haelterman, Serge Massar

We demonstrate the first opto-electronic reservoir computer with output feedback and test it on two examples of time series generation tasks: frequency and random pattern generation.

Time Series Time Series Analysis +1

Online training for high-performance analogue readout layers in photonic reservoir computers

no code implementations19 Dec 2020 Piotr Antonik, Marc Haelterman, Serge Massar

We show numerically that online learning allows to circumvent the added complexity of the analogue layer and obtain the same level of performance as with a digital layer.

Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography

no code implementations8 Feb 2018 Piotr Antonik, Marvyn Gulina, Jaël Pauwels, Serge Massar

We then show that trained reservoir computers can be used to crack chaos based cryptography and illustrate this on a chaos cryptosystem based on the Mackey-Glass system.

Embodiment of Learning in Electro-Optical Signal Processors

no code implementations20 Oct 2016 Michiel Hermans, Piotr Antonik, Marc Haelterman, Serge Massar

Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing.

speech-recognition Speech Recognition

Analog readout for optical reservoir computers

no code implementations NeurIPS 2012 Anteo Smerieri, François Duport, Yvon Paquot, Benjamin Schrauwen, Marc Haelterman, Serge Massar

Operating speeds allowing for real time information operation have been reached using optoelectronic systems.

Cannot find the paper you are looking for? You can Submit a new open access paper.