SUMMARYIn this paper a neurocomputing strategy is presented which combines data processing capabilities of neural networks and numerical structural optimization. In this strategy, an improved counterpropagation neural network is used. Two arti"cial neural networks are trained, one for the constraints and the other for the gradients of the constraints and structural optimization is accomplished by using these nets. All required parameters such as weight matrices in the neural networks or the gradient computations are automated in this neuro-optimizer strategy. Numerical examples are included to demonstrate the accuracy of the results.

The present paper, describes the applications of two artificial neural networks, namely the backpropagation neural net (BPN) and the improved counterpropagation neural net (CPN) to the analysis and design of large scale space structures. Different aspects of these nets and parameters affecting the performance of each net is investigated. Two examples are studied, both of which are oriented towards structural optimization. A comparison is made on the performance of these nets The improved CPN is trained faster than BPN, especially when large scale problems are involved. The responses of BPN and improved CPN are compared for the same input.

No abstract

As one of the most ubiquitously applied unsupervised learning methods, clustering has also been known to have a few disadvantages. More specifically, parameters such as the number of clusters and neighborhood radius are usually unknown and hard to estimate in practical cases. Moreover, the stochastic nature of a great number of these algorithms is also a considerable point of weakness. In order to address these issues, we propose DISCERN which can serve as an initialization algorithm for K-Means, finding suitable centroids that increase the performance of K-Means. Following that, the algorithm can estimate the number of clusters if need be. The algorithm does all of that, while maintaining complete robustness and returning the same results at each separate run. We ran experiments on the proposed method processing multiple datasets and the results show its undeniable superiority in terms of results, computational time and robustness when compared to the randomized K-Means and K-Means++ initialization. In addition, the superiority in estimating the number of clusters is also discussed and we prove the lower complexity when compared to methods such as the elbow and silhouette methods in estimating the number of clusters.

No abstract