[PDF][PDF] An overview of reservoir computing: theory, applications and implementations
B Schrauwen, D Verstraeten… - Proceedings of the 15th …, 2007 - biblio.ugent.be
Training recurrent neural networks is hard. Recently it has however been discovered that it
is possible to just construct a random recurrent topology, and only train a single linear …
is possible to just construct a random recurrent topology, and only train a single linear …
[图书][B] Neuromorphic photonics
PR Prucnal, BJ Shastri - 2017 - taylorfrancis.com
This book sets out to build bridges between the domains of photonic device physics and
neural networks, providing a comprehensive overview of the emerging field of" …
neural networks, providing a comprehensive overview of the emerging field of" …
Minimum complexity echo state network
Reservoir computing (RC) refers to a new class of state-space models with a fixed state
transition structure (the reservoir) and an adaptable readout form the state space. The …
transition structure (the reservoir) and an adaptable readout form the state space. The …
An experimental unification of reservoir computing methods
D Verstraeten, B Schrauwen, M d'Haene, D Stroobandt - Neural networks, 2007 - Elsevier
Three different uses of a recurrent neural network (RNN) as a reservoir that is not trained but
instead read out by a simple external classification layer have been described in the …
instead read out by a simple external classification layer have been described in the …
Reservoir computing approaches for representation and classification of multivariate time series
Classification of multivariate time series (MTS) has been tackled with a large variety of
methodologies and applied to a wide range of scenarios. Reservoir computing (RC) …
methodologies and applied to a wide range of scenarios. Reservoir computing (RC) …
Smart homes for the elderly dementia sufferers: identification and prediction of abnormal behaviour
In this paper, we have described a solution for supporting independent living of the elderly
by means of equipping their home with a simple sensor network to monitor their behaviour …
by means of equipping their home with a simple sensor network to monitor their behaviour …
Human activity recognition using multisensor data fusion based on reservoir computing
Activity recognition plays a key role in providing activity assistance and care for users in
smart homes. In this work, we present an activity recognition system that classifies in the …
smart homes. In this work, we present an activity recognition system that classifies in the …
Toward optical signal processing using photonic reservoir computing
K Vandoorne, W Dierckx, B Schrauwen… - Optics express, 2008 - opg.optica.org
We propose photonic reservoir computing as a new approach to optical signal processing in
the context of large scale pattern recognition problems. Photonic reservoir computing is a …
the context of large scale pattern recognition problems. Photonic reservoir computing is a …
Improving reservoirs using intrinsic plasticity
B Schrauwen, M Wardermann, D Verstraeten, JJ Steil… - Neurocomputing, 2008 - Elsevier
The benefits of using intrinsic plasticity (IP), an unsupervised, local, biologically inspired
adaptation rule that tunes the probability density of a neuron's output towards an exponential …
adaptation rule that tunes the probability density of a neuron's output towards an exponential …
Automatic speech recognition using a predictive echo state network classifier
MD Skowronski, JG Harris - Neural networks, 2007 - Elsevier
We have combined an echo state network (ESN) with a competitive state machine
framework to create a classification engine called the predictive ESN classifier. We derive …
framework to create a classification engine called the predictive ESN classifier. We derive …