Difference between revisions of "DSC180bW2021"
From Immersive Visualization Lab Wiki
(→Schedule) |
(→Schedule) |
||
| (One intermediate revision by one user not shown) | |||
| Line 65: | Line 65: | ||
| 9 | | 9 | ||
| Mar 3 | | Mar 3 | ||
| − | | | + | | [[Media:09_DiscussionW21.pdf|Week 9]] |
| [https://dsc-capstone.github.io/assignments/quarter-2-project/ Final Checkpoint] | | [https://dsc-capstone.github.io/assignments/quarter-2-project/ Final Checkpoint] | ||
|- | |- | ||
| 10 | | 10 | ||
| Mar 10 | | Mar 10 | ||
| − | | | + | | [[Media:10_DiscussionW21.pdf|Week 10]] |
| | | | ||
|} | |} | ||
Latest revision as of 08:57, 10 March 2021
Contents |
DSC 180B Capstone Section A01: Explainable AI
- Instructor: Jurgen Schulze
- Discussion: Wednesdays 9-9:50pm on Zoom
- Office hours: Fridays 10-11am on Zoom
- Piazza Discussion Board
Overview
In this capstone domain we are going to study how we can make machine learning systems more user friendly by exploiting additional knowledge we can derive from the system and present it to the user. These types of systems are called Explainable AI.
In this second quarter of the capstone domain, the teams that were formed in the first quarter will be working on their capstone projects. In the weekly discussions we will get updates from randomly selected teams, and also discuss anything that might be of interest to multiple/all teams.
This class will be entirely remote.
Schedule
| Week | Discussion Date | Discussion Wed 9-9:50am (Link to Slides) | Checkpoints |
|---|---|---|---|
| 1 | Jan 6 | Overview | |
| 2 | Jan 13 | Week 2 | |
| 3 | Jan 20 | Week 3 | |
| 4 | Jan 27 | Week 4 | |
| 5 | Feb 3 | Week 5 | Midterm Checkpoint due Feb 7 |
| 6 | Feb 10 | Week 6 | |
| 7 | Feb 17 | Week 7 | |
| 8 | Feb 24 | Week 8 | |
| 9 | Mar 3 | Week 9 | Final Checkpoint |
| 10 | Mar 10 | Week 10 |
Relevant Publications
- Paper on Grad-CAM algorithm: Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
- Paper on COCO image dataset: Microsoft COCO: Common Objects in Context
- Original attention map paper: Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- Learning Deep Features for Discriminative Localization
- Visualizing CNNs with deconvolution
- Deep Learning with Python by François Chollet
Useful Links
- Main DSC Capstone Website
- Introduction to how CNNs Work
- Tensorflow Playground
- Grad-CAM implementation in Pytorch
- COCO Image Dataset
- http://cs-people.bu.edu/jmzhang/excitationbp.html
Direct CNN Visualization
- https://github.com/conan7882/CNN-Visualization
- https://medium.com/@awjuliani/visualizing-neural-network-layer-activation-tensorflow-tutorial-d45f8bf7bbc4
- drawNet: http://people.csail.mit.edu/torralba/research/drawCNN/drawNet.html
- https://towardsdatascience.com/how-to-visualize-convolutional-features-in-40-lines-of-code-70b7d87b0030
- https://towardsdatascience.com/understanding-your-convolution-network-with-visualizations-a4883441533b
- http://cs231n.github.io/understanding-cnn/
