Neural networks have proven effective at solving difficult problems but designing their architectures can be challenging, even for image classification problems alone. Our goal is to minimize human participation, so we employ evolutionary algorithms to discover such networks automatically. Despite significant computational requirements, we show that it is now possible to evolve models with accuracies within the range of those published in the last year. Specifically, we employ simple evolutionary techniques at unprecedented scales to discover models for the CIFAR-10 and CIFAR-100 datasets, starting from trivial initial conditions and reaching accuracies of 94.6\% (95.6\% for ensemble) and 77.0\%, respectively. To do this, we use novel and intuitive mutation operators that navigate large search spaces; we stress that no human participation is required once evolution starts and that the output is a fully-trained model. Throughout this work, we place special emphasis on the repeatability of results, the variability in the outcomes and the computational requirements.

In this paper, we present a Web spam detection algorithm that relies on link analysis. The method consists of three steps: (1) decomposition of web graphs in densely connected sub graphs and calculation of the features for each sub graph, (2) use of SVM classifiers to identify sub graphs composed of Web spam, and (3) propagation of predictions over web graphs by a biased Page Rank algorithm to expand the scope of identification. We performed experiments on a public benchmark. An empirical study of the core structure of web graphs suggests that highly ranked non-spam hosts can be identified by viewing the coreness of the web graph elements.

Most of the faster community extraction algorithms are based on the Clauset, Newman and Moore (CNM), which is employed for networks with sizes up to 500,000 nodes. The modification proposed by Danon, Diaz and Arenas (DDA) obtains better modularity among CNM and its variations, but there is no improvement in speed as its authors expressed. In this paper, we identify some inefficiencies in the data structure employed by former algorithms. We propose a new framework for the algorithm and a modification of the DDA to make it applicable to large-scale networks. For instance, the community extraction of a network with 1 million nodes and 5 million edges was performed in about 14 minutes in contrast to former CNM that required 45 hours (192 times the former CNM, obtaining better modularity).