Course Wiki
Regularization and dropout — Machine Learning Zoomcamp Module 8
Add notes from the video (PRs are welcome)
Related Pages
Machine Learning Zoomcamp › Module 8: Neural Networks and Deep Learning › Regularization and dropout
Notes
Add notes from the video (PRs are welcome)
- A neural network might learn false patterns, i.e. if it repeatedly recognizes a certain logo on a t-shirt it might learn that the logo defines the t-shirt which is wrong since the logo might also be seen on a hoodie.
- hiding parts of the images (freeze) from being seen by the learning neural network
- dropout = randomly freezing parts of the image
- comparing different performance parameters while changing dropout rate and regularization
| ⚠️ |
The notes are written by the community. If you see an error here, please create a PR with a fix. |
Key concepts
Related notes
- mlz-m01-model-selection-process
- mlz-m02-car-price-prediction-project
- mlz-m02-car-price-prediction-project-summary
- mlz-m02-regularization
- mlz-m02-tuning-the-model
- mlz-m03-explore-more
- mlz-m06-xgboost-parameter-tuning
- mlz-m08-adding-more-layers
- mlz-m08-adjusting-the-learning-rate
- mlz-m08-checkpointing
- mlz-m08-convolutional-neural-networks
- mlz-m08-data-augmentation
- mlz-m08-explore-more
- mlz-m08-fashion-classification
- mlz-m08-installation-of-tensorflow
- mlz-m08-pre-trained-convolutional-neural-networks
- mlz-m08-summary
- mlz-m08-tensorflow-and-keras
- mlz-m08-training-a-larger-model
- mlz-m08-transfer-learning
- mlz-m08-using-the-model
- mlz-m09-introduction-to-serverless
- mlz-m09-python-3-12-vs-tf-lite-2-17