Data Science Revealed: With Feature Engineering, Data Visualization, Pipeline Development, and Hyperparameter Tuning

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2021

T. C. NokeriData Science Revealedhttps://doi.org/10.1007/978-1-4842-6870-4_12

12. Neural Networks

Tshepo Chris Nokeri¹  

(1)

Pretoria, South Africa

 

This chapter introduces a subfield of machine learning frequently recognized as deep learning. First, it introduces different artificial neural networks. Second, we cover back propagation and forward propagation. Third, it presents different activation functions. Last, it builds and test a Restricted Boltzmann Machine and a multilayer perceptron using the SciKit-Learn package, followed by deep belief networks using the Keras package. To install Keras on the Python environment, use pip install Keras and on the conda ...