Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners

© Ekaba Bisong 2019

E. . BisongBuilding Machine Learning and Deep Learning Models on Google Cloud Platformhttps://doi.org/10.1007/978-1-4842-4470-8_29

29. Training a Neural Network

Ekaba Bisong¹ 

(1)

OTTAWA, ON, Canada

 

This chapter gives an overview of the techniques for training a deep neural network. Here, we briefly discuss

• How learned information flows through a neural network

• The role of the cost function at the output layer of the network

• One-hot encoding and the softmax activation function for determining class membership at the output layer of a classification problem

• The backpropagation algorithm for improving the learned parameters of the network

• Activation functions that enable the neural network to learn non-linear patterns

In this chapter, ...