Vanishing/Exploding Gradients are two of the main problems we face when building neural networks. Before jumping into trying out fixes, it is important to understand what they mean, why they happen and what problems they cause for our neural networks. In this video, we will learn what it means for gradients to vanish or explode and we will take a quick look at what techniques there are in order to deal with vanishing or exploding gradients.
Previous lesson: [ Ссылка ]
Next lesson: TBA
📙 Here is a lesson notes booklet that summarizes everything you learn in this course in diagrams and visualizations. You can get it here 👉 [ Ссылка ]
👩💻 You can get access to all the code I develop in this course here: [ Ссылка ]
❓To get the most out of the course, don't forget to answer the end of module questions:
[ Ссылка ]
👉 You can find the answers here:
[ Ссылка ]
RESOURCES:
🏃♀️ Data Science Kick-starter mini-course: [ Ссылка ]
🐼 Pandas cheat sheet: [ Ссылка ]
📥 Streamlit template (updated in 2023, now for $5): [ Ссылка ]
📝 NNs hyperparameters cheat sheet: [ Ссылка ]
📙 Fundamentals of Deep Learning in 25 pages: [ Ссылка ]
COURSES:
👩💻 Hands-on Data Science: Complete your first portfolio project: [ Ссылка ]
🌎 Website - [ Ссылка ]
🐥 Twitter - [ Ссылка ]
