Oklahoma State University–Stillwater

About: Oklahoma State University–Stillwater is a education organization based out in Stillwater, Oklahoma, United States. It is known for research contribution in the topics: Population & Large Hadron Collider. The organization has 18267 authors who have published 36743 publications receiving 1107500 citations. The organization is also known as: Oklahoma State University & OKState.

Evolving Deep Convolutional Neural Networks for Image Classification

Abstract: Evolutionary paradigms have been successfully applied to neural network designs for two decades. Unfortunately, these methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights. In this paper, we propose a new method using genetic algorithms for evolving the architectures and connection weight initialization values of a deep convolutional neural network to address image classification problems. In the proposed algorithm, an efficient variable-length gene encoding strategy is designed to represent the different building blocks and the potentially optimal depth in convolutional neural networks. In addition, a new representation scheme is developed for effectively initializing connection weights of deep convolutional neural networks, which is expected to avoid networks getting stuck into local minimum that is typically a major issue in the backward gradient-based optimization. Furthermore, a novel fitness evaluation method is proposed to speed up the heuristic search with substantially less computational resource. The proposed algorithm is examined and compared with 22 existing algorithms on nine widely used image classification tasks, including the state-of-the-art methods. The experimental results demonstrate the remarkable superiority of the proposed algorithm over the state-of-the-art designs in terms of classification error rate and the number of parameters (weights).

Political ideology and views about climate change in the European Union

Abstract: There is a strong political divide on climate change in the US general public, with Liberals and Democrats expressing greater belief in and concern about climate change than Conservatives and Republicans. Recent studies find a similar though less pronounced divide in other countries. Its leadership in international climate policy making warrants extending this line of research to the European Union (EU). The extent of a left–right ideological divide on climate change views is examined via Eurobarometer survey data on the publics of 25 EU countries before the 2008 global financial crisis, the 2009 ‘climategate’ controversy and COP-15 in Copenhagen, and an increase in organized climate change denial campaigns. Citizens on the left consistently reported stronger belief in climate change and support for action to mitigate it than did citizens on the right in 14 Western European countries. There was no such ideological divide in 11 former Communist countries, likely due to the low political salience of...

In silico identification of conserved microRNAs in large number of diverse plant species.

Abstract: Background MicroRNAs (miRNAs) are recently discovered small non-coding RNAs that play pivotal roles in gene expression, specifically at the post-transcriptional level in plants and animals. Identification of miRNAs in large number of diverse plant species is important to understand the evolution of miRNAs and miRNA-targeted gene regulations. Now-a-days, publicly available databases play a central role in the in-silico biology. Because, at least ~21 miRNA families are conserved in higher plants, a homology based search using these databases can help identify orthologs or paralogs in plants.