Botelho, Fernanda
Absence of Cycles in Symmetric Neural Networks
Wang, Xin, Jagota, Arun K., Botelho, Fernanda, Garzon, Max H.
For an n-neuron recurrent network, a much--studied and Widely-used continuous-time (CT) model is the leaky integrator model (Hertz, et 01., 1991; Hopfield, 1984),
Absence of Cycles in Symmetric Neural Networks
Wang, Xin, Jagota, Arun K., Botelho, Fernanda, Garzon, Max H.
Abstract Missing
Stability and Observability
Garzon, Max H., Botelho, Fernanda
We present a class of feedback control functions which accelerate convergence rates of autonomous nonlinear dynamical systems such as neural network models, without affecting the basic convergence properties (e.g.
Observability of Neural Network Behavior
Garzon, Max, Botelho, Fernanda
We prove that except possibly for small exceptional sets, discretetime analogneural nets are globally observable, i.e. all their corrupted pseudo-orbitson computer simulations actually reflect the true dynamical behavior of the network. Locally finite discrete (boolean) neural networks are observable without exception.
Observability of Neural Network Behavior
Garzon, Max, Botelho, Fernanda
We prove that except possibly for small exceptional sets, discretetime analog neural nets are globally observable, i.e. all their corrupted pseudo-orbits on computer simulations actually reflect the true dynamical behavior of the network. Locally finite discrete (boolean) neural networks are observable without exception.
Stability and Observability
Garzon, Max H., Botelho, Fernanda
We present a class of feedback control functions which accelerate convergence ratesof autonomous nonlinear dynamical systems such as neural network models, without affecting the basic convergence properties (e.g.