[HTML][HTML] Emerging opportunities and challenges for the future of reservoir computing
Reservoir computing originates in the early 2000s, the core idea being to utilize dynamical
systems as reservoirs (nonlinear generalizations of standard bases) to adaptively learn …
systems as reservoirs (nonlinear generalizations of standard bases) to adaptively learn …
Artificial sensory system based on memristive devices
In the biological nervous system, the integration and cooperation of parallel system of
receptors, neurons, and synapses allow efficient detection and processing of intricate and …
receptors, neurons, and synapses allow efficient detection and processing of intricate and …
Recurrent Neural Networks and Recurrent Optical Spectrum Slicers as Equalizers in High Symbol Rate Optical Transmission Systems
The transition to the edge-cloud era makes ultra-high data rate signals indispensable for
covering the immense and increasing traffic demands created. This ecosystem also seeks …
covering the immense and increasing traffic demands created. This ecosystem also seeks …
Unconventional integrated photonic accelerators for high-throughput convolutional neural networks
We provide an overview of the rapidly evolving landscape of integrated photonic
neuromorphic architectures, specifically targeting the implementation of convolutional neural …
neuromorphic architectures, specifically targeting the implementation of convolutional neural …
[HTML][HTML] Graphene/silicon heterojunction for reconfigurable phase-relevant activation function in coherent optical neural networks
Optical neural networks (ONNs) herald a new era in information and communication
technologies and have implemented various intelligent applications. In an ONN, the …
technologies and have implemented various intelligent applications. In an ONN, the …
Universal Approximation of Linear Time-Invariant (LTI) Systems through RNNs: Power of Randomness in Reservoir Computing
Recurrent neural networks (RNNs) are known to be universal approximators of dynamic
systems under fairly mild and general assumptions. However, RNNs usually suffer from the …
systems under fairly mild and general assumptions. However, RNNs usually suffer from the …
Enhanced BaTiO3/Si3N4 integrated photonic platform with VO2 technology for large-scale neuromorphic computing
JJ Seoane, J Parra, J Navarro-Arenas… - Optical Materials …, 2023 - opg.optica.org
The hybrid barium titanate (BaTiO_3 or BTO)–silicon nitride (Si_3N_4 or SiN) platform
integrated on silicon has been established as a promising candidate for implementing …
integrated on silicon has been established as a promising candidate for implementing …
[HTML][HTML] Experimental results on nonlinear distortion compensation using photonic reservoir computing with a single set of weights for different wavelengths
E Gooskens, S Sackesyn, J Dambre, P Bienstman - Scientific Reports, 2023 - nature.com
Photonics-based computing approaches in combination with wavelength division
multiplexing offer a potential solution to modern data and bandwidth needs. This paper …
multiplexing offer a potential solution to modern data and bandwidth needs. This paper …
Low-complexity samples versus symbols-based neural network receiver for channel equalization
Low-complexity neural networks (NNs) have successfully been proposed for digital signal
processing (DSP) in short-reach intensity-modulated directly detected optical links, where …
processing (DSP) in short-reach intensity-modulated directly detected optical links, where …
Self-Coherent Receiver Based on a Recurrent Optical Spectrum Slicing Neuromorphic Accelerator
Coherent technology supporting higher order modulation formats is indispensable for
fulfilling the ever-increasing need for higher capacity. However, coherent receivers require …
fulfilling the ever-increasing need for higher capacity. However, coherent receivers require …