Deep Neural Networks in a Mathematical Framework by Anthony L. Caterini & Dong Eui Chang

Author:Anthony L. Caterini & Dong Eui Chang
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

3.4 Conclusion

In this chapter, we have developed a generic mathematical framework for layered neural networks. We have calculated derivatives with respect to the parameters of each layer for standard loss functions, demonstrating how to do this directly over the vector space in which the parameters are defined. We have also done this with a higher-order loss function which shows the flexibility of the developed framework. We will use this generic framework to represent specific network structures in the next chapter.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.