We introduce a measure for the complexity of Boolean functions that is highly correlated with the generalization ability that could be obtained when the functions are implemented on feedforward neural networks. The measure, based on the calculation of the number of neighbour examples that differ in their output value, can be simple computed from the definition of the functions, independently of...

An urban microeconomic model of households evolving in a 2D cellular automata allows to simulate the growth of a metropolitan area where land is devoted to housing, road network and agricultural/green areas. This system is self-organised: based on individualistic decisions of economic agents who compete on the land market, the model generates a metropolitan area with houses, roads, and agricult...

This paper presents a parameter modeling to Power System Stabilizers (PSS) using MLP and RBF neural networks. The application of neural networks in PSS aims to improve the dynamic stability of electric power systems by reducing the machine eletromechanic damping oscillation when a disturbance occurs. According to the current plant operating conditions, the PSS parameters are automatically adjus...

This paper proposes a new method for transmission loss allocation. The share of each bus in the transmission line losses is determined using transmission line loss equations with respect to bus-injected currents. Then, it is applied to the total network transmission lines. In the proposed method, comparing with other methods, a solution to remove the negative loss allocation has been introd...

An anonymous ring network is a ring where all processors (vertices) are totally indistinguishable except for their input value. Initially, to each vertex of the ring is associated a value from a totally ordered set; thus, forming a multiset. In this paper we consider the problem of sorting such a distributed multiset and we investigate its relationship with the election problem. We focus on the...

As an alternative to synthesis-by-rule, the use of neural networks in speech synthesis has been successfully applied to prosody generation, yet it is not known precisely which input parameters are responsible for good results. The approach presented here tries to quantify the contribution of each input parameter. This is done first by comparing the mean errors of networks trained with only one ...

We construct a provably secure mix-net from any CCA2 secure cryptosystem. The mix-net is secure against active adversaries that statically corrupt less than λ out of k mix-servers, where λ is a threshold parameter, and it is robust provided that at most min(λ− 1, k − λ) mix-servers are corrupted. The main component of our construction is a mix-net that outputs the correct result if all mix-serv...

We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO Nets). DISCO Nets allow us to efficiently sample from a posterior distribution parametrised by a neural network. During training, DISCO Nets are learned by minimising the dissimilarity coefficient between the true distribution and the estimated distribution. This allows us to tailor the training...

a critical protection requirement for grid connected distributed generators (dg) is anti-islanding protection. in this paper, a new islanding detection method for any possible network loading is proposed based on utilizing and combining various system parameter indices. in order to secure the detection of islanding, eight intentional disturbances are imposed to the system under study in which t...