What are 1x1 Convolutions in Deep Learning?

You might have come across 1x1 convolution in deep learning architecture and wondered why they were there. In this tutorial, I'll walk you through their usefulness and how they compare to other dimensionality reduction techniques.
Table of Content
- Introduction: 0:00
- 1x1 in networks: 0:11
- Convolutions: 1:40
- How to reduce dimensionality: 2:48
- What is 1x1 convolution doing?: 4:25
- Pooling vs 1x1 convolution: 6:44
- Conclusion: 7:19
Here are some other resources that are very good on this topic:
📌 StackOverflow Question on the Subject: stats.stackexchange.com/quest...
📌 A Gentle Introduction to 1×1 Convolutions to Manage Model Complexity: machinelearningmastery.com/in...
📌 How are 1x1 convolutions the same as a fully connected layer? (Another StackOverflow Question): datascience.stackexchange.com...
📌 DeepLearningAI Video on the Subject: • C4W2L05 Network In Net...
📌 A Gentle Introduction to Pooling Layers for Convolutional Neural Networks: machinelearningmastery.com/po...
Really great content, check it out! ☝️
----
Join the Discord for general discussion: / discord
----
Follow Me Online Here:
Twitter: / yacineaxya
GitHub: github.com/yacineMahdid
LinkedIn: / yacinemahdid
___
Have a great week! 👋

[@luisluiscunha]

You made this concept so easy to understand: thank you!

[@machinelearningexplained]

I am glad it was useful :)

[@pachecotaboadaandrejoaquin6727]

Thank you for breaking it down so well! Keep up the excellent work!

[@machinelearningexplained]

Hey thanks for the kind words!
Will do, I have a few more videos ready for next week :)
Do let me know if there is a specific topic or question you would like covered!

[@rafa_br34]

Very useful indeed, I just think the 3D representation could be a bit better (I'm used to seeing the filter rectangle behind the first layer and not on the side, but that's probably just me)

[@machinelearningexplained]

True, it’s titled by about 90 degrees.
Otherwise the 1x1 convolution wouldn’t fit well in the image I believe.

[@JuliusSmith]

Shouldn't we call it a 1 x 1 x Cin convolution?

[@machinelearningexplained]

That would indeed be a less confusing name for sure. That thing already have like 7 different names though haha

[@HeyySujal]

I like your explanations, but Im watching it randomly
As I'm beginner, where should I start?

[@machinelearningexplained]

Glad you liked it.
It’s the second time this week I had this request for where to start in deep learning, I’m setting up a video on that topic will publish soon!