Neural Networks and Their Internal Processes: From the ground up
Kutenkov, Ilia (2022)
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2022063019197
https://urn.fi/URN:NBN:fi:amk-2022063019197
Tiivistelmä
The theses’ aim is to explain and practically show the operation of different types of neural networks. Thesis will prove that they all have the same main idea at the core but have different goals, methods and components. The thesis also shows a process of preparing a custom object detection dataset that could be used for training neural networks.
Author decided to show the neural networks from the ground up. First, he is explaining an abstract operation of a chosen tool. Then, a mathematical explanation is written. Finally, the code implementation or use case of a tool is shown.
As a result, thesis has a lot of information about neural networks with a code examples associated. It also contains an explanation of processes that happen in neural network during their forward and backward operations. 3 different datasets were used to train neural networks. The thesis’ goals were successfully achieved.
Author decided to show the neural networks from the ground up. First, he is explaining an abstract operation of a chosen tool. Then, a mathematical explanation is written. Finally, the code implementation or use case of a tool is shown.
As a result, thesis has a lot of information about neural networks with a code examples associated. It also contains an explanation of processes that happen in neural network during their forward and backward operations. 3 different datasets were used to train neural networks. The thesis’ goals were successfully achieved.