Next we will divulge into fastai, what the library aims to do, and why it can be considered a "library for all." Afterwards we will close by showing examples of what a "model" is and how to utilize the framework at a high level to complete your Deep Learning tasks. In broad strokes, this article will cover what exactly a "Jupyter Notebook" is and why it is popular among the Machine Learning community. My specific interests involve speeding up the framework for deployment, tabular neural networks, and providing overall usage guides to help further the community What will we cover in this article? I'm also heavily involved inside the fastai community, of which I would emplore you to join! My goal is to make fastai more approachable at all levels through examples and help further Jeremy's dream in the process. At the time of writing this I'm still an Undergraduate at the University of West Florida majoring in Computer Science. I've designed my own course geared around the library from an implementation standpoint without getting too complex. My name is Zach Mueller, I've extensively been involved and using fastai (and the newest version) for the better part of two years now.
Finally, the last article will briefly explain the advanced artifacts inside of fastai and how they all function. The intermediate article comes from a perspective of those who utilized the original fastai library in the past and understand the broad strokes of the library. This article is geared towards those who have barely heard of "Deep Learning" and have zero experience with frameworks. The "Zero to Hero" series is a collection of three seperate articles geared towards getting anyone familair with the fastai library based upon their skill sets.
0 kommentar(er)
