Devising deep latent variable models for multi-modal data has been a
lon...
Numerical evaluations of the memory capacity (MC) of recurrent neural
ne...
Reservoir computing approximation and generalization bounds are proved f...
On Euclidean spaces, the Gaussian kernel is one of the most widely used
...
A universal kernel is constructed whose sections approximate any causal ...
Reservoir computing systems are constructed using a driven dynamical sys...
This paper shows that the celebrated Embedding Theorem of Takens is a
pa...
Echo state networks (ESNs) have been recently proved to be universal
app...
A new explanation of geometric nature of the reservoir computing phenome...
Many recurrent neural network machine learning paradigms can be formulat...
The notion of memory capacity, originally introduced for echo state and
...
This work studies approximation based on single-hidden-layer feedforward...
We analyze the practices of reservoir computing in the framework of
stat...
Much effort has been devoted in the last two decades to characterize the...
The universal approximation properties with respect to L ^p -type criter...
This paper shows that echo state networks are universal uniform approxim...
A new class of non-homogeneous state-affine systems is introduced. Suffi...
This paper characterizes the conditional distribution properties of the
...
This paper addresses the reservoir design problem in the context of
dela...
This paper extends the notion of information processing capacity for
non...