All Hyperparameters of a Neural Network Explained

Neural Networks have a lot of knobs and buttons you have to set correctly to get the best possible performance out of it. Although some of them are self-explanatory and easy to understand (like the number of neurons in the input layer) and choose, there are many hyperparameters that are a bit more complex in terms of how they affect the outcome of the model (e.g. number of layers, the batch size or weight initialization).

In this lesson, we will take an overall look at all possible hyperparameters and understand on a high level what they mean and how they affect the performance of the network. In the coming lessons, we will dive deeper into the details of these hyperparameters.

Previous lesson: https://youtu.be/aNOWNu-grcQ
Next lesson: https://youtu.be/YhatZb5SzE0

📙 Here is a lesson notes booklet that summarizes everything you learn in this course in diagrams and visualizations. You can get it here 👉 https://misraturp.gumroad.com/l/fdl

👩‍💻 You can get access to all the code I develop in this course here: https://github.com/misraturp/Deep-learning-course-repo

❓To get the most out of the course, don't forget to answer the end of module questions:
https://fishy-dessert-4fc.notion.site/Deep-Learning-101-Questions-35797462583d43a3adcea9478bfe035d

👉 You can find the answers here:
https://fishy-dessert-4fc.notion.site/Deep-Learning-101-Answers-f90449595add492fb9dd8db3859662e3

RESOURCES:
🏃‍♀️ Data Science Kick-starter mini-course: https://misraturp.gumroad.com/l/kick-starter
🐼 Pandas cheat sheet: https://misraturp.gumroad.com/l/pandascs
📙 Fundamentals of Deep Learning in 25 pages: https://misraturp.gumroad.com/l/fdl

🌎 Website - https://misraturp.com/
🐥 Twitter - https://twitter.com/misraturp

Видео All Hyperparameters of a Neural Network Explained канала Mısra Turp