update description

DESCRIPTION

@@ -1,12 +1,12 @@
 Package: deeplearning
 Type: Package
 Title: An Implementation of Deep Neural Network for Regression and Classification
-Description: An implementation of deep neural network with rectifier linear units (ReLU) trained
-	with stochastic gradient descent (SGD) method and batch normalization. A combination of these methods have
+Description: 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 (Sergey Ioffe 2015)
-	and dropout (Nitish Srivastava 2014) are implemented as regularization. The deeplearning package is inspired by
-	the darch package and uses its class DArch.
+	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.
 Version: 0.1.0
 Date: 2016-04-10
 Authors@R: c(