This lab and the accompanying lecture answers the questions "What is deep learning?", "What makes it different from other kinds of machine learning?" and "How do you do deep learning?".
The main takeaway and learning outcome is that
Deep learning is a search for good hierarchical representations...
...that makes a given task easy to solve. Our objective is to get everyone on board with this description of deep learning, and to indicate why and when deep learning can be useful. I will also provide hands-on experience with how this translates into computer code (using PyTorch) via some concrete, simple examples.
ELMED219-2022-Lab3-Video-Introduction
ELMED219-2022-Lab3-Video-Examples
| Notebook | 1-Click Notebook |
|---|---|
| ELMED219-2022-Lab3-DL-Example-1-image_classification-MedNIST-using-PyTorch.ipynb provides a translation of the lecture's description of deep learning into PyTorch code, using a simple image classification example (the MedMIST data set collected by Dr. Bradley J. Erickson). |
 |
| ELMED219-2022-Lab3-DL-Example-2-image_classification-using-fastai.ipynb repeats the above story by using more advanced image classification techniques, and also extends it to more difficult data sets. |
|
| Extra-ELMED219-2022-Lab3-DL-Example-3-image_segmentation.ipynb gives an example of deep learning applied to medical image segmentation. |
|
| Extra-Extra-ELMED219-2022-Lab3-DL-Example-4-segmentation-brain-tumor-using-MONAI.ipynb shows an example of deep learning applied to brain tumor segmentation from MRI. |
|