Geometrical image features like edges and ridges in digital images may be extracted by convolving the images with appropriate derivatives of Gaussians. The choice of the convolution operator and of the parameters of the Gaussian involved de nes a speci c feature image. In this paper, various feature images derived from CT and MR brain images are de ned and tested for usability and robustness in...

A formula (X) with one free monadic predicate variable de nes the set of predicates (or family of point-sets) on A that satisfy (X). This family is said to be de nable by (X) in A: Suppose that A is a subchain of B = hB; <i. With a formula (X; A) we associate the following family of point-sets (or set of predicates) fP : P A and (P;A) holds in Bg on A: This family is said to be de nable by in A...

Common selection mechanisms used in Evolutionary Algorithms are combined to form some generalized variants of selection. These are applied to a Genetic Algorithm and are subject to an experimental comparison. The feature of extinctiveness as introduced in Evolution Strategies is identiied to be the main reason for a considerable speedup of the search in case of unimodal objective functions .

This study further investigates the complete-basis-functions parameterization method (CBFP) for Evolution Strategies (ES), and its application to a challenging real-life high-dimensional physics optimization problem, namely Femtosecond Laser Pulse Shaping. The CBFP method, which was introduced recently for tackling efficiently the learning task of n-variables functions, is combined here, for th...

In this paper, we show universal lower bounds for isotropic algorithms, that hold for any algorithm such that each new point is the sum of one already visited point plus one random isotropic direction multiplied by any step size (whenever the step size is chosen by an oracle with arbitrarily high computational power). The bound is 1−O(1/d) for the constant in the linear convergence, as already ...

Assume that some objects are present in an image but can be seen only partially and are overlapping each other. To recognize the objects , we have to rstly separate the objects from one another, and then match them against the modeled objects using partial observation. This paper presents a probabilistic approach for solving this problem. Firstly, the task is formulated as a two-stage optimal e...

This paper presents an experimental study of different variants of tournament selection, and proposes a new DISPAR-tournament (Disjoint Sets Parallel tournament) operator for population reduction to be used in parallel implementations of evolution strategies and other evolutionary algorithms.

Wireless Sensor Networks (WSN) have been studied intensively for various applications such as monitoring and surveillance. Sensor deployment is an essential part of WSN, because it affects both the cost and capability of the sensor network. However, most deployment schemes proposed so far have been based on over-simplified assumptions, where results may be far from optimal in practice. Our prop...

According to a theorem by Astete-Morales, Cauwet, and Teytaud, “simple Evolution Strategies (ES)” that optimize quadratic functions disturbed by additive Gaussian noise of constant variance can only reach a simple regret log-log convergence slope ≥ −1/2 (lower bound). In this paper a population size controlled ES is presented that is able to perform better than the −1/2 limit. It is shown exper...

An enterprise that uses evolving software is susceptible to destructive and even disastrous effects caused either by inadvertent errors, or by malicious attacks by the programmers employed to maintain this software. It is my thesis that these perils of evolving software can often be tamed by ensuring that suitable overarching principles are maintained as invariants of the evolution of a given s...