Interference in neural networks occurs when learning in one area of the input space causes unlearning in another area. Networks that are less susceptible to interference are referred to as spatially local networks. To obtain a better understanding of these properties, a theoretical framework, consisting of a measure of interference and a measure of network localization, is developed. These meas...

Real-valued random hidden variables can be useful for modelling latent structure that explains correlations among observed variables. I propose a simple unit that adds zero-mean Gaussian noise to its input before passing it through a sigmoidal squashing function. Such units can produce a variety of useful behaviors, ranging from deterministic to binary stochastic to continuous stochastic. I sho...

In this paper we s h o w that the loading problem for a 3-node architecture with sigmoidal activation is NP-hard if the input dimension varies, if the classiication is performed with a certain accuracy, and if the output weights are restricted.

We investigate the computational power of recurrent neural networks that apply the sigmoid activation function _(x)=[2 (1+e)]&1. These networks are extensively used in automatic learning of non-linear dynamical behavior. We show that in the noiseless model, there exists a universal architecture that can be used to compute any recursive (Turing) function. This is the first result of its kind for...

Abstr,,ct. In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set ofaffine functionals can uniformly approximate any continuous function of n real variables with support in the unit hypercube; only mild conditions are imposed on the univariate function. Our results settle an open question about representability in the class of sing...

For the Weibulland Richards-regression model robust designs are determined by maximizing a minimum of Dor D1-efficiencies, taken over a certain range of the non-linear parameters. It is demonstrated that the derived designs yield a satisfactory solution of the optimal design problem for this type of model in the sense that these designs are efficient and robust with respect to misspecification ...

We generalize a result of Gao and Xu [4] concerning the approximation of functions of bounded variation by linear combinations of a fixed sigmoidal function to the class of functions of bounded φ-variation (Theorem 2.7). Also, in the case of one variable, [1: Proposition 1] is improved. Our proofs are similar to that of [4].

Abstr,,ct. In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set ofaffine functionals can uniformly approximate any continuous function of n real variables with support in the unit hypercube; only mild conditions are imposed on the univariate function. Our results settle an open question about representability in the class of sing...

From genetic regulatory networks to nervous systems, the interactions between elements in biological networks often take a sigmoidal or S-shaped form. This paper develops a probabilistic characterization of the parameter space of continuous-time sigmoidal networks (CTSNs), a simple but dynamically-universal model of such interactions. We describe an efficient and accurate method for calculating...

Multi-class pattern recognition has a wide range of applications including handwritten digit recognition (Chiang, 1998), speech tagging and recognition (Athanaselis, Bakamidis, Dologlou, Cowie, Douglas-Cowie & Cox, 2005), bioinformatics (Mahony, Benos, Smith & Golden, 2006) and text categorization (Massey, 2003). This chapter presents a comprehensive and competitive study in multi-class neural ...