Learn R Programming

softmaxreg (version 1.2)

Training Multi-Layer Neural Network for Softmax Regression and Classification

Description

Implementation of 'softmax' regression and classification models with multiple layer neural network. It can be used for many tasks like word embedding based document classification, 'MNIST' dataset handwritten digit recognition and so on. Multiple optimization algorithm including 'SGD', 'Adagrad', 'RMSprop', 'Moment', 'NAG', etc are also provided.

Copy Link

Version

Install

install.packages('softmaxreg')

Monthly Downloads

10

Version

1.2

License

GPL (>= 2)

Maintainer

Xichen Ding

Last Published

September 9th, 2016

Functions in softmaxreg (1.2)

softmaxreg-internal

Internal Softmaxreg Functions
trainModel

Train softmax regression and classification model
loadURLData

Download and Unzip Web Datasets
document

Easy Implementation to Read Multiple Documents within the Folder
softmax-class

Class "softmax"
BIC.softmax

Calculate BIC of Fitted Softmax Regression Model
softmaxReg

Fit Multi-Layer Softmax Regression or Classification Model
convertClass2Matrix

Convert A Vector of Factors to Matrix
AIC.softmax

Calculate AIC of Fitted Softmax Regression Model
word2vec

Pre-trained Word2vec Dataset from Corpus
wordEmbed

Embed Words to Vectors Using Pre-trained Word2vec Dictionary