The evolution of two-dimensional neural network models with rank one connecting matrices and saturated linear transfer functions is dynamically equivalent to that of piecewise linear maps on an interval. It is shown that their iterative behavior ranges from being highly predictable, where almost every orbit accumulates to an attracting fixed point, to the existence of chaotic regions with cycles of arbitrarily large period
The Recurrent Neural Networks (RNNs) represent an important class of bio-inspired learning machines ...
Most theoretical studies of the computational capabilities of balanced, recurrent E/I networks assu...
In this paper, we explore the dynamical features of a neural network model which presents two types ...
Local dynamics in a neural network are described by a two-dimensional (backpropagation or Hebbian) m...
We examine the approximating power of recurrent networks for dynamical systems through an unbounded ...
On account of their role played in the fundamental biological rhythms and by considering their pote...
summary:The dynamical behaviour of a continuous time recurrent neural network model with a special w...
(A) Two-dimensional phase diagram, showing the fraction of positive Lyapunov exponents as a functio...
Chaos in dynamical systems potentially provides many different dynamical states arising from a singl...
Recurrent neural network models with parallel distributed architecture are constructed using ordinar...
We investigate the predictive power of recurrent neural networks for oscillatory systems not only on...
Abstract—Chaotic neural networks have received a great deal of attention these last years. In this p...
Many forms of recurrent neural networks can be understood in terms of dynamic systems theory of diff...
It has been known for a short time that a class of recurrent neural networks has universal computati...
The difficult problems of predicting chaotic time series and modelling chaotic systems is approached...
The Recurrent Neural Networks (RNNs) represent an important class of bio-inspired learning machines ...
Most theoretical studies of the computational capabilities of balanced, recurrent E/I networks assu...
In this paper, we explore the dynamical features of a neural network model which presents two types ...
Local dynamics in a neural network are described by a two-dimensional (backpropagation or Hebbian) m...
We examine the approximating power of recurrent networks for dynamical systems through an unbounded ...
On account of their role played in the fundamental biological rhythms and by considering their pote...
summary:The dynamical behaviour of a continuous time recurrent neural network model with a special w...
(A) Two-dimensional phase diagram, showing the fraction of positive Lyapunov exponents as a functio...
Chaos in dynamical systems potentially provides many different dynamical states arising from a singl...
Recurrent neural network models with parallel distributed architecture are constructed using ordinar...
We investigate the predictive power of recurrent neural networks for oscillatory systems not only on...
Abstract—Chaotic neural networks have received a great deal of attention these last years. In this p...
Many forms of recurrent neural networks can be understood in terms of dynamic systems theory of diff...
It has been known for a short time that a class of recurrent neural networks has universal computati...
The difficult problems of predicting chaotic time series and modelling chaotic systems is approached...
The Recurrent Neural Networks (RNNs) represent an important class of bio-inspired learning machines ...
Most theoretical studies of the computational capabilities of balanced, recurrent E/I networks assu...
In this paper, we explore the dynamical features of a neural network model which presents two types ...
DOI
Add to ORKG