Think “whole game approach”: It is like learning baseball, you go to a game, learn to play bit by bit (and already enjoy), and later you can hone you skills and learn all the physics involved, instead of the other way around. Don’t worry, you’ll get to the nitty gritty details soon enough. This approach might have its benefits, it will take a long(er) time and a lot of perseverence to get to useful results.įast.ai uses a complete opposite, top-down approach by teaching you to create results right away and gradually introducing more and more of the concepts/details as you go along. They make sure you understand the required linear algebra/math, non-linear functions, partial derivatives to then gradually introduce neural networks, much like most school/university courses are taught. Most deep learning courses start from the bottom and work their way up, first explaining all the basic elements and then combining them. The practical, top-down approach of fast.ai using a coding focussed approach, without dumbing it down.Get you up and running with deep learning in practice,. ![]() Interesting links / Links from the lessonįast.ai tries to achieve these three goals:.Digging a little deeper: The basics of Convolutional Networks.Putting it all together: examples of deep learning.All-purpose parameter fitting: gradient Descent.Infinitely flexible function: A neural network.Artificial Intelligence > Machine Learning > Deep Learning.Side note: Getting the data - PDL - Python Download Library.How to build your own classifier using the fast.ai library.Why we need a GPU and where to access them.How to run Python code in Jupyter notebooks.The practical, top-down approach of fast.ai.Lesson takeawaysīy the end of the lesson you should know/understand Maybe they can be of help to you as well. As part of this process I’m writing down more detailed notes to help me better understand the material. I’m taking the course for a second time, which means I’m re-watching the videos, reading the papers and making sure I am able to reproduce the code. These are my annotated notes from the first lesson of the first part of the Fast.ai course. ![]() You will get a feel for what deep learning is and why it works, as well as possible applications you can build yourself. The first lesson gives an introduction into the why and how of the fast.ai course, and you will learn the basics of Jupyter Notebooks and how to use the fast.ai library to build a world-class image classifier in three lines of Python. ![]() This blog post covers the 2018 course which you can find here.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |