The following pages link to (Q5214289):
Displaying 12 items.
- Embedding and approximation theorems for echo state networks (Q1982435) (← links)
- The universal approximation property. Characterization, construction, representation, and existence (Q2043428) (← links)
- Dimension reduction in recurrent networks by canonicalization (Q2076953) (← links)
- Memory and forecasting capacities of nonlinear recurrent networks (Q2116285) (← links)
- The echo index and multistability in input-driven recurrent neural networks (Q2127403) (← links)
- Embedding information onto a dynamical system (Q5028389) (← links)
- (Q5149035) (← links)
- Stability and memory-loss go hand-in-hand: three results in dynamics and computation (Q5161146) (← links)
- Fading memory echo state networks are universal (Q6078702) (← links)
- Transport in reservoir computing (Q6098252) (← links)
- Approximation bounds for random neural networks and reservoir systems (Q6103961) (← links)
- Designing universal causal deep learning models: The geometric (Hyper)transformer (Q6196301) (← links)
