Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
@1202kbs
1202kbs committed Feb 2, 2018
1 parent 678deba commit 1bd6239
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@ In this section, we first introduce the concept of relevance score with Sensitiv

## 3 Gradient Based Methods

In this section, we explore various types of gradient-based visualization methods such as Deconvolution, Backpropagation, Guided Backpropagation, Integrated Gradients and SmoothGrad. Check out [grad.py](https://github.com/1202kbs/Understanding-NN/blob/master/models/grad.py), a modular implementation of various gradient-based visualization techniques.
Implementation of various types of gradient-based visualization methods such as Deconvolution, Backpropagation, Guided Backpropagation, Integrated Gradients and SmoothGrad. Check out [grad.py](https://github.com/1202kbs/Understanding-NN/blob/master/models/grad.py), a modular implementation of various gradient-based visualization techniques.


### 3.1 Deconvolution
Expand Down Expand Up @@ -145,7 +145,7 @@ In this section, we explore various types of gradient-based visualization method

## 4 Class Activation Map

In this section, we go through the basic Class Activation Map (CAM) and its generalized version, Grad-CAM.
Implementation of Class Activation Map (CAM) and its generalized version, Grad-CAM on the [cluttered MNIST](https://github.com/deepmind/mnist-cluttered) dataset.


### 4.1 Class Activation Map
Expand Down

0 comments on commit 1bd6239

Please sign in to comment.