Related papers: Experimental reservoir computing with diffractivel…
Reservoir computing (RC) has received recent interest because reservoir weights do not need to be trained, enabling extremely low-resource consumption implementations, which could have a transformative impact on edge computing and in-situ…
OpenReservoirComputing (ORC) is a Python library for reservoir computing (RC) written in JAX (Bradbury et al. 2018) and Equinox (Kidger and Garcia 2021). JAX is a Python library for high-performance numerical computing that enables…
The use of cavity to manipulate photon emission of quantum dots (QDs) has been opening unprecedented opportunities for realizing quantum functional nanophotonic devices and also quantum information devices. In particular, in the field of…
Reservoir computing (RC) represents a class of state-space models (SSMs) characterized by a fixed state transition mechanism (the reservoir) and a flexible readout layer that maps from the state space. It is a paradigm of computational…
We demonstrate first experimental investigation on the performance of a single-node reservoir computer based on a silicon microring resonator (MRR) operating on the digit recognition task. The input layer of the reservoir is composed of a…
Reservoir computing (RC) is an emerging recurrent neural network architecture that has attracted growing attention for its low training cost and modest hardware requirements. Memristor-based circuits are particularly promising for RC, as…
Physical reservoir computing is a computational framework that implements spatiotemporal information processing directly within physical systems. By exciting nonlinear dynamical systems and creating linear models from their state, we can…
A reservoir computer is a way of using a high dimensional dynamical system for computation. One way to construct a reservoir computer is by connecting a set of nonlinear nodes into a network. Because the network creates feedback between…
Physical reservoir computing, which is a promising method for the implementation of highly efficient artificial intelligence devices, requires a physical system with nonlinearity, fading memory, and the ability to map in high dimensions.…
Microring resonators (MRRs) are promising devices for time-delay photonic reservoir computing, but the impact of the different physical effects taking place in the MRRs on the reservoir computing performance is yet to be fully understood.…
Reservoir Computing (RC) is a bio-inspired machine learning framework, and various models have been proposed. RC is a well-suited model for time series data processing, but there is a trade-off between memory capacity and nonlinearity. In…
Vertical cavity Surface Emitting Laser (VCSEL) diodes emit light in two polarization modes. The amount of optical feedback is found to influence the intensities of the emitted modes. We investigate the effect of the amount of total output…
We introduce chaos-controlled Reservoir Computing (cc-RC) for living neural cultures: dynamically rich substrates of unique potential for adaptive computation. To account for intrinsic biological variability, cc-RC combines: (i)…
Multifunctionality describes the capacity for a neural network to perform multiple mutually exclusive tasks without altering its network connections; and is an emerging area of interest in the reservoir computing machine learning paradigm.…
Reservoir computing offers an energy-efficient alternative to deep neural networks (DNNs) by replacing complex hidden layers with a fixed nonlinear system and training only the final layer. This work investigates nanoelectromechanical…
We couple a double-channel imaging technique, allowing for the simultaneous acquisition of high-quality and high-resolution intensity and peak emission wavelength profiles [T. Wang and G.L. Lippi, Rev. Sci. Instr. 86, 063111 (2015)], to the…
Over recent years, increasingly complex approaches based on sophisticated convolutional neural network architectures have been slowly pushing performance on well-established benchmark datasets. In this paper, we take a step back to examine…
Surrogate modeling of non-linear oscillator networks remains challenging due to discrepancies between simplified analytical models and real-world complexity. To bridge this gap, we investigate hybrid reservoir computing, combining reservoir…
We miniaturize a vertically-coupled in-plane whispering gallery mode cavity incorporating a quantum cascade gain medium, aiming to realize the mid-infrared counterpart to the vertical cavity surface emitting laser (VCSEL). Building on…
Physical reservoir computing is a promising framework for efficient neuromorphic in and near-sensor computing applications. Here, we demonstrate a multimodal optoelectronic reservoir network based on halide perovskite semiconductor devices,…