NLP Demystified 7: Building Models (ML modelling overview, bias, variance, evaluation)
Vložit
- čas přidán 2. 08. 2024
- Course playlist: • Natural Language Proce...
Through a high-level overview of modelling, we'll
- clearly define "machine learning"
- look at the different types of machine learning
- learn how to evaluate model performance
- learn what bias and variance are
- see what to do about overfitting and underfitting
- explore practical concerns for model deployment.
If you're familiar with the process of building ML models, you can skip this module.
No colab notebook for this module.
Timestamps:
00:00:00 Building models
00:01:03 Scenarios for using machine learning
00:01:42 Defining machine learning
00:02:05 The different types of machine learning
00:04:20 Machine learning as automatic programming
00:05:59 A high-level view of modelling workflow
00:09:17 High bias and what to do about it
00:10:25 High variance and what to do about it
00:12:08 Regularization and hyperparameters
00:13:09 Evaluating on the test set
00:14:00 Practical concerns beyond performance metric
00:15:25 Modelling recap
This video is part of Natural Language Processing Demystified --a free, accessible course on NLP.
Visit www.nlpdemystified.org/ to learn more.
Best explanation. Crisp and exhaustive.
I've watched a couple of videos and I am truly stunned. How on earth is it possible for this series to have only ...a couple of dozen views?! This is hands down the best intro course I've ever encountered. You've done an outstanding job sir - and even that's an understatement! :)
Thank you! Your comment made my day.
I agree. I was truly shocked to see so few views on what are some of the best lessons on the topic. I'm going to create an X account just to promote the channel.
I'm a research Scholar and came across your channel. I was truly amazed at how you broke through the concepts and explained them.
Thank you!
Amazing content. I appreciate the effort you have put into making this series and will recommend it everywhere possible. Let's get this channel a significant number of views. Totally deserved. Keep up the excellent work.
Thank you!
Excellent stuff
Timestamps:
00:00:00 Building models
00:01:03 Scenarios for using machine learning
00:01:42 Defining machine learning
00:02:05 The different types of machine learning
00:04:20 Machine learning as automatic programming
00:05:59 A high-level view of modelling workflow
00:09:17 High bias and what to do about it
00:10:25 High variance and what to do about it
00:12:08 Regularization and hyperparameters
00:13:09 Evaluating on the test set
00:14:00 Practical concerns beyond performance metric
00:15:25 Modelling recap
It would be great if u can help us in giving the ppt of the context that u present in the videos, the best way to source it out will be embedding it in your website. Love ur content❤
For a deeper clarification, when does a model become become a model?
You definitely need to change the name of the channel, "t15" is not memorable and you'll get fewer clicks than you deserve for awesome material like this.
Thanks for the inspiration and for the candid feedback. I named the channel. I need to explore the branding a bit but this is the direction I'll go with.