Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning
From MaRDI portal
Publication:2373498
Recommendations
- Functional identification of biological neural networks using reservoir adaptation for point processes
- Reservoirs learn to learn
- Homeostatic plasticity for single node delay-coupled reservoir computing
- An experimental unification of reservoir computing methods
- A reservoir computing model of reward-modulated motor learning and automaticity
Cites work
- Isolated word recognition with the Liquid State Machine: a case study
- Movement Generation with Circuits of Spiking Neurons
- Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Recurrent Neural Networks with Small Weights Implement Definite Memory Machines
- Sufficient and necessary conditions for global exponential stability of discrete-time recurrent neural networks
- Synergies Between Intrinsic and Synaptic Plasticity Mechanisms
Cited in
(16)- A modified batch intrinsic plasticity method for pre-training the random coefficients of extreme learning machines
- Computational modeling of spiking neural network with learning rules from STDP and intrinsic plasticity
- Reservoirs learn to learn
- A decentralized training algorithm for echo state networks in distributed big data applications
- Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons
- Reservoir computing approaches to recurrent neural network training
- Dynamical systems as temporal feature spaces
- Functional identification of biological neural networks using reservoir adaptation for point processes
- Readouts for echo-state networks built using locally regularized orthogonal forward regression
- A reservoir computing model of reward-modulated motor learning and automaticity
- Homeostatic plasticity for single node delay-coupled reservoir computing
- Adaptive dynamical networks
- A double-cycle echo state network topology for time series prediction
- Higher-order interactions, adaptivity, and phase transitions in a novel reservoir computing model
- A constrained regularization approach for input-driven recurrent neural networks
- Role of short-term plasticity and slow temporal dynamics in enhancing time series prediction with a brain-inspired recurrent neural network
This page was built for publication: Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2373498)
