Artificial neural networks are systems prominently used in computation and investigations of biological neural systems. They provide state-of-the-art performance in challenging problems like the prediction of chaotic signals. Yet, the understanding of how neural networks actually solve problems like prediction remains vague; the black-box analogy is often employed. Merging nonlinear dynamical systems theory with machine learning, we develop a new concept which describes neural networks and prediction within the same framework. Taking profit of the obtained insight, we a-priori design a hybrid computer, which extends a neural network by an external memory. Furthermore, we identify mechanisms based on spatio-temporal synchronization with whic...
Neural networks are currently implemented on digital Von Neumann machines, which do not fully levera...
Nonlinear photonic delay systems present interesting implementation platforms for machine learning m...
The interplay between randomness and optimization has always been a major theme in the design of neu...
Artificial neural networks are systems prominently used in computation and investigations of biologi...
Les réseaux de neurones artificiels constituent des systèmes alternatifs pour effectuer des calculs ...
Reservoir Computing (RC) is a currently emerging new brain-inspired computational paradigm, which ap...
Nowadays most of computers are still based on concepts developed more than 60 years ago by Alan Turi...
Le Reservoir Computing (RC) est un paradigme s’inspirant du cerveau humain, apparu récemment au débu...
Driven by the remarkable breakthroughs during the past decade, photonics neural networks have experi...
International audienceWe report on the experimental demonstration of a hybrid optoelectronic neuromo...
The thesis develops a novel approach to design of a reservoir computer, one of the challenges of mod...
The thesis develops a novel approach to design of a reservoir computer, one of the challenges of mod...
We review a novel paradigm that has emerged in analogue neuromorphic optical computing. The goal is ...
How does the brain compute complex tasks? Is it possible to create en artificial brain? In order to ...
The recent progress in artificial intelligence has spurred renewed interest in hardware implementati...
Neural networks are currently implemented on digital Von Neumann machines, which do not fully levera...
Nonlinear photonic delay systems present interesting implementation platforms for machine learning m...
The interplay between randomness and optimization has always been a major theme in the design of neu...
Artificial neural networks are systems prominently used in computation and investigations of biologi...
Les réseaux de neurones artificiels constituent des systèmes alternatifs pour effectuer des calculs ...
Reservoir Computing (RC) is a currently emerging new brain-inspired computational paradigm, which ap...
Nowadays most of computers are still based on concepts developed more than 60 years ago by Alan Turi...
Le Reservoir Computing (RC) est un paradigme s’inspirant du cerveau humain, apparu récemment au débu...
Driven by the remarkable breakthroughs during the past decade, photonics neural networks have experi...
International audienceWe report on the experimental demonstration of a hybrid optoelectronic neuromo...
The thesis develops a novel approach to design of a reservoir computer, one of the challenges of mod...
The thesis develops a novel approach to design of a reservoir computer, one of the challenges of mod...
We review a novel paradigm that has emerged in analogue neuromorphic optical computing. The goal is ...
How does the brain compute complex tasks? Is it possible to create en artificial brain? In order to ...
The recent progress in artificial intelligence has spurred renewed interest in hardware implementati...
Neural networks are currently implemented on digital Von Neumann machines, which do not fully levera...
Nonlinear photonic delay systems present interesting implementation platforms for machine learning m...
The interplay between randomness and optimization has always been a major theme in the design of neu...