Home > dokuwiki-plugin-pubutils

dokuwiki-plugin-pubutils

Dokuwiki-plugin-pubutils is a project mainly written in PHP and JAVASCRIPT, based on the GPL-3.0 license.

DokuWiki plugin to create foldable sections for the Abstract and BibTeX entry of a publication.

DokuWiki Publication Utilities Plugin

DokuWiki plugin to create foldable sections for the Abstract and BibTeX entry of a publication.

Required plugins: jQuery plugin (https://github.com/cosmocode/dokuwiki-plugin-jquery)

Syntax: [PUB] Abstract [~~~] BibTeX [PUB]

Example: [~~PUB] In this paper we present the implementation of a framework for accelerating training and classification of arbitrary Convolutional Neural Networks (CNNs) on the GPU. CNNs are a derivative of standard Multilayer Perceptron (MLP) neural networks optimized for two-dimensional pattern recognition problems such as Optical Character Recognition (OCR) or face detection. We describe the basic parts of a CNN and demonstrate the performance and scalability improvement that can be achieved by shifting the computation-intensive tasks of a CNN to the GPU. Depending on the network topology training and classification on the GPU performs 2 to 24 times faster than on the CPU. Furthermore, the GPU version scales much better than the CPU implementation with respect to the network size. [~~~] @INPROCEEDINGS{Strigl2010-CNNGPU, author = {D. Strigl and K. Kofler and S. Podlipnig}, title = {{Performance and Scalability of GPU-based Convolutional Neural Networks}}, booktitle = {Proceedings of the 18th Euromicro International Conference on Parallel, Distributed and Network-Based Computing (PDP 2010)}, pages = {317--324}, address = {Pisa, Italy}, month = {February}, year = {2010} } [PUB~~]

See COPYING and file headers for license info.

Previous:nyuszipajtasok