English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We present the first public release of our generic neural network trainingalgorithm, called SkyNet. This efficient and robust machine learning tool isable to train large and deep feed-forward neural networks, includingautoencoders, for use in a wide range of supervised and unsupervised learningapplications, such as regression, classification, density estimation,clustering and dimensionality reduction. SkyNet uses a `pre-training' method toobtain a set of network parameters that has empirically been shown to be closeto a good solution, followed by further optimisation using a regularisedvariant of Newton's method, where the level of regularisation is determined andadjusted automatically; the latter uses second-order derivative information toimprove convergence, but without the need to evaluate or store the full Hessianmatrix, by using a fast approximate method to calculate Hessian-vectorproducts. This combination of methods allows for the training of complicatednetworks that are difficult to optimise using standard backpropagationtechniques. SkyNet employs convergence criteria that naturally preventoverfitting, and also includes a fast algorithm for estimating the accuracy ofnetwork outputs. The utility and flexibility of SkyNet are demonstrated byapplication to a number of toy problems, and to astronomical problems focusingon the recovery of structure from blurred and noisy images, the identificationof gamma-ray bursters, and the compression and denoising of galaxy images. TheSkyNet software, which is implemented in standard ANSI C and fully parallelisedusing MPI, is available at http://www.mrao.cam.ac.uk/software/skynet/.

SKYNET: an efficient and robust neural network training tool for machine learning in astronomy