Demystifying Deep Learning Building Blocks
Building deep learning models proposed by third parties can become a simple task when specialized libraries are used. However, much mysterystill surrounds the design of newmodelsorthe modification of existing ones. These tasks require in-depth knowledge of the different components or building blocks...
Αποθηκεύτηκε σε:
| Κύριος συγγραφέας: | |
|---|---|
| Άλλοι συγγραφείς: | , |
| Μορφή: | Artículo |
| Γλώσσα: | en_US |
| Έκδοση: |
2024
|
| Θέματα: | |
| Διαθέσιμο Online: | https://doi.org/10.3390/math12020296 https://www.mdpi.com/2227-7390/12/2/296#:~:text=Demystifying%20Deep%20Learning%20Building%20Blocks%201%201.%20Introduction,3.%20Theoretical%20Foundations%20of%20Deep%20Learning%203.1.%20 |
| Ετικέτες: |
Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!
|
| Περίληψη: | Building deep learning models proposed by third parties can become a simple task when specialized libraries are used. However, much mysterystill surrounds the design of newmodelsorthe modification of existing ones. These tasks require in-depth knowledge of the different components or building blocks and their dimensions. This information is limited and broken up in different literature. In this article, we collect and explain the building blocks used to design deep learning models in depth, starting from the artificial neuron to the concepts involved in building deep neural networks. Furthermore, the implementation of each building block is exemplified using the Keras library. |
|---|