Beginning Deep Learning with TensorFlow: Work with Keras, MNIST Data Sets, and Advanced Neural Networks

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2022

L. Long, X. ZengBeginning Deep Learning with TensorFlowhttps://doi.org/10.1007/978-1-4842-7915-1_7

7. Backward Propagation Algorithm

Xiangming Zeng¹   and Liangqu Long²

(1)

State College, PA, USA

(2)

Shenzhen, Guangdong, China

 

The longer you look back, the farther you can look forward.

—Winston S. Churchill

In Chapter 6, we have systematically introduced the basic neural network algorithm: starting from the representation of inputs and outputs; introducing the perceptron model, multi-input and multi-output fully connected layers; and then expanding to multilayer neural networks. We also introduced the design of the output layer under different scenarios and the ...