Layer: Layer of a DeepBeliefNet

In xrobin/DeepLearning: Deep Learning of neural networks

Description

This class represents a layer of the DeepBeliefNet.

Layer creates and returns a single layer of class layer, while Layers returns a list of Layers of the given sizes, input and output. Hidden (or internal) layers are of type “binary” by default.

Usage

Layer(size, type)

Layers(sizes, input, output, hidden = "binary")

Arguments

size, sizes	the number(s) of nodes of the Layer(s). Will be truncated to integers.
type, input, output, hidden	the type of the Layer, or for Layer the types of input, output and hidden layers. If omitted, hidden layers will be implicitly assigned a “binary” type. input and output layer types must be specified explicitly.

Value

an object of class layer containing the following elements:

• sizenumber of nodes

• typetypes of the nodes. Valid types are “binary”, “continuous” or “gaussian”

Examples

Layer(10L, "gaussian")
Layers(c(10L, 5L, 2L), "gaussian", "gaussian")

xrobin/DeepLearning documentation built on Sept. 18, 2020, 5:23 a.m.