Modern Deep Learning Design and Application Development: Versatile Tools to Solve Deep Learning Problems

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

A. YeModern Deep Learning Design and Application Developmenthttps://doi.org/10.1007/978-1-4842-7413-2_7

7. Reframing Difficult Deep Learning Problems

Andre Ye¹  

(1)

Redmond, WA, USA

 

Successful transformations reframe the problem that makes the solution possible. They erase existing boundaries and start from scratch.

—Malcolm Gladwell, Journalist and Author

To speak very roughly, the deep learning process can be represented with three central sequentially connected components: the creation of the architecture, the definition of training procedures and methods, and the training of the model itself. This is the general deep learning modeling workflow. Each of ...