fitTeachNet2 {TeachNet}

One step in backpropagation

Description

One step in the backpropagation algorithm for a two hidden layers network

Usage

fitTeachNet2(data, weights, hidden.structure, learning.rate, f, f_d, decay, m_f, er)

Arguments

data

the data set

weights

current weights

hidden.structure

vector with first element the number of hidden neurons in the first hidden layer second element for the second hidden layer

learning.rate

rate by which factor for backpropagation gets smaller

f

activation function

f_d

derivative of activation function

decay

value of weight decay

m_f

interim value m

er

error function

Value

returns the new weight after gradient update

Author(s)

Georg Steinbuss