assignment3.md - layout page mathjax true permalink assignments2015\/assignment3 In the previous assignment you implemented and trained your own

assignment3.md - layout page mathjax true permalink...

This preview shows page 1 - 2 out of 2 pages.

---layout: pagemathjax: truepermalink: assignments2015/assignment3/---In the previous assignment, you implemented and trained your own ConvNets.In this assignment, we will explore many of the ideas we have discussed inlectures. Specifically, you will:- Reduce overfitting using **dropout** and **data augmentation**- Combine models into **ensembles** to boost performance- Use **transfer learning** to adapt a pretrained model to a new dataset- Use data gradients to visualize **saliency maps** and create **fooling images**## SetupYou can work on the assignment in one of two ways: locally on your own machine, or on a virtual machine through [Terminal]().### Working locally**Get the code:**Download the starter code [here]().**[Optional] virtual environment:**Once you have unzipped the starter code, you might want to create a[virtual environment]()for the project. If you choose not to use a virtual environment, it is up to you

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture