init_nn: Initialize network

In simpleMLP: Simple Multilayer Perceptron Neural Network

Description

Initialize 3 layer fully connected neural network, also known as multilayer perceptron, setting biases to 0 and using the Xavier initialization method for weights.

Usage

init_nn(num_inputs, num_hidden_1, num_hidden_2, num_outputs)

Arguments

num_inputs	dimension of inputs
num_hidden_1	dimension of first hidden layer
num_hidden_2	dimension of second hidden layer
num_outputs	dimension of output

Value

list containing weight and bias matrices in each layer of the network

Examples

mlp_model <- init_nn(784, 100, 50, 10)

simpleMLP documentation built on March 28, 2021, 9:07 a.m.