Difference between revisions of "DSC Capstone2020"

From Immersive Visualization Lab Wiki
Jump to: navigation, search
(Useful Links)
(Useful Links)
Line 87: Line 87:
 
* [https://github.com/jacobgil/pytorch-grad-cam Grad-CAM implementation in Pytorch]
 
* [https://github.com/jacobgil/pytorch-grad-cam Grad-CAM implementation in Pytorch]
 
* [https://cocodataset.org COCO Image Dataset]
 
* [https://cocodataset.org COCO Image Dataset]
 +
 +
* What CNN layer outputs look like in Tensorflow:
 +
** https://github.com/conan7882/CNN-Visualization/tree/master/doc/firstfilter#visualization-of-filters-and-feature-maps-of-googlenet
 +
** https://medium.com/@awjuliani/visualizing-neural-network-layer-activation-tensorflow-tutorial-d45f8bf7bbc4
 +
 +
* Paper on visualzing CNNs with deconvolution: https://arxiv.org/pdf/1311.2901.pdf
 +
* Various ways to visualize diverse information in CNNs: https://github.com/conan7882/CNN-Visualization
 +
* Interesting visualization: http://people.csail.mit.edu/torralba/research/drawCNN/drawNet.html
 +
* More stuff:
 +
** 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/
 +
** http://cs-people.bu.edu/jmzhang/excitationbp.html

Revision as of 22:59, 6 October 2020

Contents

DSC 180 Capstone Domain: Explainable AI (Section A01)

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.

The example we are going to use in this class is object recognition in images. We are first going to go over the basics of CNNs, then learn about saliency and attention maps, and finally we are going to implement the Grad-CAM algorithm in PyTorch and apply it to the COCO image data set.

The quarter will end with a proposal for your capstone project, which you will be working on in the winter quarter.

This class will be entirely remote.

Schedule

Week Date Discussion Topic Replication Tasks
1 Oct 7 Overview None for week 1
2 Oct 14 Literature review
3 Oct 21 Description of data
4 Oct 28 Checkpoint #1 due
5 Nov 4 Description of methods
6 Nov 11 Veterans Day (No Discussion) Implementation of methods
7 Nov 18 Checkpoint #2 due
8 Nov 25 Implementation of Grad-CAM
9 Dec 2 Implementation of Grad-CAM
10 Dec 9 Final Report due

Papers

Useful Links