https://github.com/aharley/nn_vis

An interactive visualization of neural networks
https://github.com/aharley/nn_vis

Last synced: about 2 months ago
JSON representation

An interactive visualization of neural networks

• Host: GitHub
• URL: https://github.com/aharley/nn_vis
• Owner: aharley
• License: mit
• Created: 2016-01-26T18:37:45.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2023-12-01T06:42:14.000Z (10 months ago)
• Last Synced: 2024-01-28T23:10:40.972Z (8 months ago)
• Language: JavaScript
• Size: 3.73 MB
• Stars: 233
• Watchers: 9
• Forks: 49
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# An Interactive Node-Link Visualization of Convolutional Neural Networks

![alt text](images/seven.png)

## Abstract

Convolutional neural networks are at the core of state-of-the-art approaches to a variety of computer vision tasks. Visualizations of neural networks typically take the form of static node-link diagrams, which illustrate only the structure of a network, rather than the behavior. Motivated by this observation, this project presents a new interactive visualization of neural networks trained on handwritten digit recognition, with the intent of showing the actual behavior of the network given user-provided input. The user can interact with the network through a drawing pad, and watch the activation patterns of the network respond in real time.

## Paper PDF

![paper](images/paper.png)

## Live demos

Live demos for all models are available at [https://adamharley.com/nn_vis](https://adamharley.com/nn_vis):

1. 3d visualization of a multi-layer perceptron:

   ![cnn2d](images/mlp_3d.png)

2. 3d visualization of a convolutional network:

   ![cnn2d](images/cnn_3d.png)

3. 2d visualization of a multi-layer perceptron:

   ![cnn2d](images/mlp_2d.png)

4. 2d visualization of a convolutional network:

   ![cnn2d](images/cnn_2d.png)

## FAQ

* Can I use this in my course/textbook/presentation?

  * Yes! Please just cite the work appropriately.

  

* How do I cite you?

  * Here is a plaintext citation:

  

    `A. W. Harley, "An Interactive Node-Link Visualization of Convolutional Neural Networks," in ISVC, pages 867-877, 2015`

  

    Here is a bibtex snippet:

    ```

    @inproceedings{harley2015isvc,

    title = {An Interactive Node-Link Visualization of Convolutional Neural Networks},

    author = {Adam W Harley},

    booktitle = {ISVC},

    pages = {867--877},

    year = {2015}

    }

    ```

    

* I tried to run the code locally, and I see classifications, but I do not see the network visualization. What's wrong?

  * This is probably related to json requests being blocked by something called `CORS policy`. The solution is to upload the code to a web address and run it from there, instead of running locally.

Contact: [email protected]