86 citations · 305 across the 8 of their papers we have counts for
8 papers
Random pattern and frequency generation using a photonic reservoir computer with output feedback
Piotr Antonik, Michiel Hermans, Marc Haelterman +1
Reservoir computing is a bio-inspired computing paradigm for processing time dependent signals. The performance of its analogue implementations matches other digital algorithms on…
A Differentiable Physics Engine for Deep Learning in Robotics
Jonas Degrave, Michiel Hermans, Joni Dambre +1
An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivati…
Embodiment of Learning in Electro-Optical Signal Processors
Michiel Hermans, Piotr Antonik, Marc Haelterman +1
Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular it has recently been d…
Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation
Piotr Antonik, François Duport, Michiel Hermans +3
Reservoir Computing is a bio-inspired computing paradigm for processing time dependent signals. The performance of its analogue implementation are comparable to other state of the…
Towards Trainable Media: Using Waves for Neural Network-Style Training
Michiel Hermans, Thomas Van Vaerenbergh
In this paper we study the concept of using the interaction between waves and a trainable medium in order to construct a matrix-vector multiplier. In particular we study such a dev…
Photonic Delay Systems as Machine Learning Implementations
Michiel Hermans, Miguel Soriano, Joni Dambre +2
Nonlinear photonic delay systems present interesting implementation platforms for machine learning models. They can be extremely fast, offer great degrees of parallelism and potent…
Trainable and Dynamic Computing: Error Backpropagation through Physical Media
Michiel Hermans, Michaël Burm, Joni Dambre +1
Machine learning algorithms, and more in particular neural networks, arguably experience a revolution in terms of performance. Currently, the best systems we have for speech recogn…
Memristor models for machine learning
Juan Pablo Carbajal, Joni Dambre, Michiel Hermans +1
In the quest for alternatives to traditional CMOS, it is being suggested that digital computing efficiency and power can be improved by matching the precision to the application. M…