Convolutional highways are deep networks based on multiple stacked convolutional layers for feature preprocessing. We introduce an evolutionary algorithm (EA) for optimization of the structure and hyperparameters of convolutional highways and demonstrate the potential of this optimization setting on the well-known MNIST data set. The (1+1)-EA employs Rechenberg’s mutation rate control and a nic...

This paper introduces a modification on the movement force vector of the Birbil and Fang’s electromagnetism-like algorithm [1] for solving global optimization problems with bounded variables. The proposed movement vector combines the total force exerted on each point of the population, at the current iteration, with the rate of change in the force vector of a previous iteration. Several widely ...

In this paper, an evolutionary algorithm, called EA-WDND, is developed to optimize water distribution network design for real instances. The evolutionary algorithm uses the Epanet Solver which, while not an optimizer, helps to evaluate the operational constraints of mass conservation, energy conservation, pressure in nodes (nodal heads) of the network, and velocities of water in network pipes. ...

A method that allows us to give a different treatment to any neuron inside feedforward neural networks is presented. The algorithm has been implemented with two very different learning methods: a standard Back-propagation (BP) procedure and an evolutionary algorithm. First, we have demonstrated that the EA training method converges faster and gives more accurate results than BP. Then we have ma...

For problems involving uncertainties in design variables and parameters, a bi-objective evolutionary algorithm (EA) based approach to design optimization using evidence theory is proposed and implemented in this paper. In addition to a functional objective, a plausibility measure of failure of constraint satisfaction is minimized. Despite some interests in classical optimization literature, thi...

The ability of an evolutionary algorithm (EA) to adapt its search strategy during the optimization process is a central concept in evolutionary computation, because (i) the best setting of an EA is not known a priori for a given task, (ii) the optimal search strategy is normally not constant during the evolutionary process. Thinking in terms of search (or generating) distributions, population a...

Cluster structure optimization (CSO) refers to finding the globally minimal cluster structure with respect to a specific model and quality criterion, and is a computationally extraordinarily hard problem. Here we report a successful hybridization of evolutionary algorithms (EAs) with local heat pulses (LHPs). We describe the algorithm’s implementation and assess its performance with hard benchm...

We apply entropy agglomeration (EA), a recently introduced algorithm, to cluster the words of a literary text. EA is a greedy agglomerative procedure that minimizes projection entropy (PE), a function that can quantify the segmentedness of an element set. To apply it, the text is reduced to a feature allocation, a combinatorial object to represent the word occurences in the text’s paragraphs. T...

The rst contribution of this paper is a theoretical comparison of the (1+1)-EA evolutionary algorithm to other evolutionary algorithms in the case of so-called monotone reproduction operator, which indicates that the (1+1)-EA is an optimal search technique in this setting. After that we study the expected optimization time for the (1+1)-EA and show two set covering problem families where it is ...