This paper proposes use of feed-forward neural networks and external state feedback to produce an equivalent recurrent neural network equivalent. The external feedback enables explicit storage and analysis of the state
This paper describes a special type of dynamic neural network called the Recursive Neural Network (R...
This paper proposes five partially recurrent neural networks architectures to evaluate the different...
In this paper, we show how a set of recently derived theoretical results for recurrent neural networ...
This paper suggests the use of Fourier-type activation functions in fully recurrent neural networks....
An RNN can in principle map from the entire history of previous inputs to each output. The idea is t...
This paper aims to discuss and analyze the potentialities of Recurrent Neural Networks (RNN) in cont...
Recurrent neural networks can be used for both the identification and control of nonlinear systems. ...
Non-relaxing recurrent neural networks (RNNs) generalize feedforward neural networks (FFNNs) in a st...
The report introduces a constructive learning algorithm for recurrent neural networks, which modifie...
SummaryMemory storage on short timescales is thought to be maintained by neuronal activity that pers...
The architecture of a neural network controlling an unknown environment is presented. It is based on...
Recurrent Neural Networks (RNNs) are connectionist models that operate in discrete time using feedba...
This paper illustrates how internal model control of nonlinear processes can be achieved by recurren...
WOS: 000244970900005PubMed ID: 17385626The architecture and training procedure of a novel recurrent ...
This paper concerns dynamic neural networks for signal processing: architectural issues are consider...
This paper describes a special type of dynamic neural network called the Recursive Neural Network (R...
This paper proposes five partially recurrent neural networks architectures to evaluate the different...
In this paper, we show how a set of recently derived theoretical results for recurrent neural networ...
This paper suggests the use of Fourier-type activation functions in fully recurrent neural networks....
An RNN can in principle map from the entire history of previous inputs to each output. The idea is t...
This paper aims to discuss and analyze the potentialities of Recurrent Neural Networks (RNN) in cont...
Recurrent neural networks can be used for both the identification and control of nonlinear systems. ...
Non-relaxing recurrent neural networks (RNNs) generalize feedforward neural networks (FFNNs) in a st...
The report introduces a constructive learning algorithm for recurrent neural networks, which modifie...
SummaryMemory storage on short timescales is thought to be maintained by neuronal activity that pers...
The architecture of a neural network controlling an unknown environment is presented. It is based on...
Recurrent Neural Networks (RNNs) are connectionist models that operate in discrete time using feedba...
This paper illustrates how internal model control of nonlinear processes can be achieved by recurren...
WOS: 000244970900005PubMed ID: 17385626The architecture and training procedure of a novel recurrent ...
This paper concerns dynamic neural networks for signal processing: architectural issues are consider...
This paper describes a special type of dynamic neural network called the Recursive Neural Network (R...
This paper proposes five partially recurrent neural networks architectures to evaluate the different...
In this paper, we show how a set of recently derived theoretical results for recurrent neural networ...
DOI
Add to ORKG