From d625f8fa449ea91bc51ff6dab89397200c7d5b36 Mon Sep 17 00:00:00 2001 From: aharley Date: Thu, 30 Nov 2023 22:42:13 -0800 Subject: [PATCH] reorganized to make the important stuff easier to find --- index.html | 49 +++++++++++++++++++++++++++++-------------------- 1 file changed, 29 insertions(+), 20 deletions(-) diff --git a/index.html b/index.html index 52419d8..a7bafe4 100644 --- a/index.html +++ b/index.html @@ -134,24 +134,7 @@

An Interactive Node-Link Visualization of Convolutional Neural Networks

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 paper 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

-
- An Interactive Node-Link Visualization of Convolutional Neural Networks -
-

Citation

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

Bibtex format:

-
- - @inproceedings{harley2015isvc,
-     title = {An Interactive Node-Link Visualization of Convolutional Neural Networks},
-     author = {Adam W Harley},
-     booktitle = {ISVC},
-     pages = {867--877},
-     year = {2015}
- } -
-
+

Demo

@@ -199,8 +182,34 @@

Demo

-

Details

-

The networks were trained on an augmented version of MNIST, so they excel at categorizing centred upright numbers. The networks were trained in a custom neural network implementation in MATLAB; the math for the visualizations was written in Javascript; the visualization was created in WebGL. The source code for both visualizations is available here.

+

Code and implementation details

+

Our source code is freely available on github here.

+

A few details that might be interesting: +

+

Paper

+
+ An Interactive Node-Link Visualization of Convolutional Neural Networks +
+

Citation

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

Bibtex format:

+
+ + @inproceedings{harley2015isvc,
+     title = {An Interactive Node-Link Visualization of Convolutional Neural Networks},
+     author = {Adam W Harley},
+     booktitle = {ISVC},
+     pages = {867--877},
+     year = {2015}
+ } +
+
+