deeplearning: An Implementation of Deep Neural Network for Regression and Classification
Version 0.1.0

An implementation of deep neural network with rectifier linear units trained with stochastic gradient descent method and batch normalization. A combination of these methods have achieved state-of-the-art performance in ImageNet classification by overcoming the gradient saturation problem experienced by many deep architecture neural network models in the past. In addition, batch normalization and dropout are implemented as a means of regularization. The deeplearning package is inspired by the darch package and uses its class DArch.

Getting started

Package details

AuthorZhi Ruan [aut, cre], Martin Drees [cph]
Date of publication2016-04-11 18:09:06
MaintainerZhi Ruan <[email protected]>
LicenseGPL (>= 2)
Version0.1.0
URL https://github.com/rz1988/deeplearning
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:
install.packages("deeplearning")

Try the deeplearning package in your browser

Any scripts or data that you put into this service are public.

deeplearning documentation built on Jan. 15, 2017, 9:52 a.m.