Torres, J. J., Marro, J., Cortes, J. M., Wemmenhove, B.
We present and study a probabilistic neural automaton in which the fraction of simultaneously-updated neurons is a parameter, rho (0, 1) . For small rho, there is relaxation towards one of the...
Loop corrected belief propagation (2007)
We propose a method for improving Belief Propagation (BP) that takes into account the influence of loops in the graphical model. The method is a variation on and generalization of the method recently...
On Cavity Approximations for Graphical Models (2006)
Rizzo, T., Wemmenhove, B., Kappen, H. J.
We reformulate the Cavity Approximation (CA), a class of algorithms recently introduced for improving the Bethe approximation estimates of marginals in graphical models. In our new formulation, which...
Sensitivity, Itinerancy and Chaos in Partly-Synchronized Weighted Networks (2006)
Marro, J., Torres, J. J., Cortes, J. M., Wemmenhove, B.
We present exact results, as well as some illustrative Monte Carlo simulations, concerning a stochastic network with weighted connections in which the fraction of nodes that are dynamically...
Survey propagation at finite temperature: application to a Sourlas code as a toy model (2005)
In this paper we investigate a finite temperature generalization of survey propagation, by applying it to the problem of finite temperature decoding of a biased finite connectivity Sourlas code for...
Finitely connected vector spin systems with random matrix interactions (2005)
Coolen, A., Skantzos, N. S., Castillo, I. Perez, Vicente, C. J. Perez, Hatchett, J. P. L., Wemmenhove, B., ...
We use finite connectivity equilibrium replica theory to solve models of finitely connected unit-length vectorial spins, with random pair-interactions which are of the orthogonal matrix type. Since...
Replica symmetry breaking in the `small world' spin glass (2004)
Wemmenhove, B, Nikoletopoulos, T, Hatchett, J P L
We apply the cavity method to a spin glass model on a `small world' lattice, a random bond graph super-imposed upon a 1-dimensional ferromagnetic ring. We show the correspondence with a replicated...
Slowly evolving random graphs II: Adaptive geometry in finite-connectivity Hopfield models (2004)
Wemmenhove, B., Skantzos, N. S.
We present an analytically solvable random graph model in which the connections between the nodes can evolve in time, adiabatically slowly compared to the dynamics of the nodes. We apply the...
Analytic solution of attractor neural networks on scale-free graphs (2004)
Castillo, I. Pérez, Wemmenhove, B., Hatchett, J. P. L., Coolen, A. C. C., Skantzos, N. S., Nikoletopoulos, T.
We study the influence of network topology on retrieval properties of recurrent neural networks, using replica techniques for diluted systems. The theory is presented for a network with an arbitrary...
Slowly evolving geometry in recurrent neural networks I: extreme dilution regime (2004)
Wemmenhove, B., Skantzos, N. S., Coolen, A. C. C.
We study extremely diluted spin models of neural networks in which the connectivity evolves in time, although adiabatically slowly compared to the neurons, according to stochastic equations which on...
Parallel dynamics of disordered Ising spin systems on finitely connected random graphs (2004)
Hatchett, J. P. L., Wemmenhove, B., Castillo, I. Perez, Nikoletopoulos, T., Skantzos, N. S., Coolen, A. C. C.
We study the dynamics of bond-disordered Ising spin systems on random graphs with finite connectivity, using generating functional analysis. Rather than disorder-averaged correlation and response...
Replicated Transfer Matrix Analysis of Ising Spin Models on `Small World' Lattices (2004)
Nikoletopoulos, T., Coolen, A. C. C., Perez-Castillo, I., Skantzos, N. S., Hatchett, J. P. L., Wemmenhove, B.
We calculate equilibrium solutions for Ising spin models on `small world' lattices, which are constructed by super-imposing random and sparse Poissonian graphs with finite average connectivity c onto...
Analytic solution of attractor neural networks on scale-free graphs (2004)
Perez Castillo, I., Wemmenhove, B., Hatchett, J.P.L., Coolen, A.C.C., Skantzos, N.S., Nikoletopoulos, T.
Replicated transfer matrix analysis of Ising spin models on 'small world' lattices (2004)
Nikoletopoulos, T., Coolen, A.C.C., Perez Castillo, I., Skantzos, N.S., Hatchett, J.P.L., Wemmenhove, B.
Parallel dynamics of disordered Ising spin systems on finitely connected random graphs (2004)
Hatchett, J.P.L., Wemmenhove, B., Perez-Castillo, I., Nikoletopoulos, T., Skantzos, N.S., Coolen, A.C.C.
Combining Hebbian and reinforcement learning in a minibrain model (2004)
Bosman, R.J.C., Leeuwen, W.A. Van, Wemmenhove, B.
A toy model of a neural network in which both Hebbian learning and reinforcement learning occur is studied. The problem of ‘path interference’, which makes that the neural net quickly forgets...
Replicated transfer matrix analysis of Ising spin (2004)
Models On Small, T Nikoletopoulos, I Pérez Castillo, B Wemmenhove
We calculate equilibrium solutions for Ising spin models on `small world' lattices, which are constructed by super-imposing random and sparse Poissonian graphs with finite average connectivity c...
Wemmenhove Perez Castillo, B Wemmenhove, I Pérez Castillo, T Nikoletopoulos, N S Skantzos, ...
We study the dynamics of bond-disordered Ising spin systems on random graphs with finite connectivity, using generating functional analysis. Rather than disorder-averaged correlation and response...
Analytic Solution of Attractor Neural Networks on Scale-Free Graphs (2004)
I Perez Castillo, B Wemmenhove, N S Skantzos, T Nikoletopoulos
We study the influence of network topology on retrieval properties of recurrent neural networks, using replica techniques for diluted systems. The theory is presented for a network with an arbitrary...
Finite Connectivity Attractor Neural Networks (2003)
Wemmenhove, B., Coolen, A. C. C.
We study a family of diluted attractor neural networks with a finite average number of (symmetric) connections per neuron. As in finite connectivity spin glasses, their equilibrium properties are...
Combining Hebbian and reinforcement learning in a minibrain model (2003)
Bosman, R. J. C., Van Leeuwen, W. A., Wemmenhove, B.
A toy model of a neural network in which both Hebbian learning and reinforcement learning occur is studied. The problem of `path interference', which makes that the neural net quickly forgets...
Learning by a nerual net in a noisy environment - The pseudo-inverse solution revisited (2002)
Van Leeuwen, W A, Wemmenhove, B
A recurrent neural net is described that learns a set of patterns in the presence of noise. The learning rule is of Hebbian type, and, if noise would be absent during the learning process, the...