Regularization in a Neural Network explained

In this video, we explain the concept of regularization in an artificial neural network and also show how to specify regularization in code with Keras.

🕒🦎 VIDEO SECTIONS 🦎🕒

00:30 Help deeplizard add video timestamps - See example in the description
05:25 Collective Intelligence and the DEEPLIZARD HIVEMIND

💥🦎 DEEPLIZARD COMMUNITY RESOURCES 🦎💥

👋 Hey, we're Chris and Mandy, the creators of deeplizard!
👀 CHECK OUT OUR VLOG:

👉 Check out the blog post and other resources for this video:

💻 DOWNLOAD ACCESS TO CODE FILES
🤖 Available for members of the deeplizard hivemind:

🧠 Support collective intelligence, join the deeplizard hivemind:

🤜 Support collective intelligence, create a quiz question for this video:

🚀 Boost collective intelligence by sharing this video on social media!

❤️🦎 Special thanks to the following polymaths of the deeplizard hivemind:
Tammy
Prash
Zach Wimpee

👀 Follow deeplizard:

🎓 Deep Learning with deeplizard:

🎓 Other Courses:

🛒 Check out products deeplizard recommends on Amazon:

📕 Get a FREE 30-day Audible trial and 2 FREE audio books using deeplizard's link:

🎵 deeplizard uses music by Kevin MacLeod

❤️ Please use the knowledge gained from deeplizard content for good, not evil.

[CosmiaNebula]

0:14 intro
1:09 L2 regularization
3:00 why regularization
4:15 Keras

[vtrandal]

Absolutely brilliant! DeepLizard is now among my favorites for Deep Learning architecture and tuning concepts. Thank you for making this video.

[tymothylim]

Thank you very much for this video! It gave me a good grasp of what regularization is, what it's for, and how it's implemented in Keras!

[mohaliyet]

Simple, direct, informative and helpful! Thank you a million!

[Joe-qpow]

Watching or listening to your video is really a good way for me to learn new stuff comfortably and quickly. Accurate explanations, useful example, implemented codes, everything is awesome. Thank you!

[qusayhamad]

thank you very much for this clear and helpful explanation.
Words fail to express my gratitude.

[abderrahmanedjerourou]

I really love this channel. Thank you so much. Great work.

[adwaitnaik]

your videos are beyond amazing with to the point and lucid explanation. Thanks

[fritz-c]

I spotted a slight issue in the article for this video.

The article ends by saying "We are ready now to look at the concept of a learning rate. I'll see ya there.", but the next article in line (by clicking the "Next" button) is for Batch Size.

I really enjoy your courses so far, by the way. I've stopped and started a few times with studying ML in the past, but this has been a pleasure to go through.

[Nissearne]

Thank's again Like the whole "deeplizard" serie. Explain thing's I want to understand more, I feel often like a clown when I try and test and play with some basic of Neural Network, but you help me to understand more.

[AvinashSingh-bkkg]

Heard your voice in Hitman 2 Silent Assasin game.
"47 this is your agent Diana from
By the way,
Very helpful content ♥️ !👍

[smritisings]

Hey, I recommended these videos to everybody interested to learn about Deep Learning. I love that your videos don't exceed 7minutes, has a good explanation, good implementation in keras--perfect

The only thing that would make it even better is if you could add links to documents that you mentioned in your video: for example: a link to all regularization functons by keras. It would be a complete learning tool then.
Keep making these videos foreverr!

[shivamjuna]

you've really good voice..and really informative.

[vladiklass]

amazing how you break down the topics to such short, simple and well understandable videos! Great job

[michaelmuller]

Great, I think i've understood it now! Informative and to the point, thank you!

[sivakumar-homw]

Really helped me to understand the concept Thanks

[kkhanhy]

I like your lectures... keep it up, really beneficial!

[haseebshah]

I had been looking for this for so long!

[richarda]

again another fantastic video :) may I suggest that for the Jupyter noteblook portions (for here and other videos) especially if there are only a few cells, can you please magnify the images? maybe to even 3x bigger? if I'm watching on my phone or tablet, that would help immensely :) Thanks alot :D

[manuelkarner]

okay very nice video but: regularization penelizeses to much network complexity ... this is done by adding a term to the loss function that penelizes large weights -> but I dont get the connection, why is the model complexity incresing if the weights get bigger ?
3:50 there you explained it :)
So is it realy only about decreasing weights & because of that having very little or 0-weights, which means less connenctions between the neurons OR are there more reasons to the correlation between weight "size" & model complexity ?