ReVACNN

Steering Convolutional Neural Network via Real-Time Visual Analytics

Abstract

Recently, deep learning has become exceptionally popular due to its outstanding performances in various machine learning and artificial intelligence applications. Convolutional neural network (CNN), a representative model of deep learning, has been successfully applied to solve computationally burdening tasks in various applications like computer vision. Despite its outstanding capability, training a CNN model properly is time-consuming and prone to overfitting and/or bad local minima. To address these issues, this study aims at improving the interpretation of the training process and using it for subsequent human intervention, specifically steering the training process of CNN model in the real time. In this paper, we present ReVACNN, a real-time visual analytic system for CNN, where (1) the overall training process (e.g., the amount of activations and that of changes each filter/layer has at a particular iteration/epoch) is visualized in network view and (2) the 2D embedding of trained filters within layers is visualized to show the relationships between filters as well as layers. In particular, ReVACNN allows users to perform several interactions in real time: (1) skipping the gradient descent update on the sub-part of a CNN model to reduce the subsequent training time and (2) steering filters interactively in the 2D embedding view to avoid bad local minima. At the end, we present several use cases that demonstrate the benefits users can gain from ReVACNN.


Here is the presentation I gave at NIPS’16-FILM.

Here is the ReVACNN demo.

Slides from the presentation. Click here to see in full size.

Want to learn more?

Cite this work

@inproceedings{chung2016re, title={Re-VACNN: Steering convolutional neural network via real-time visual analytics}, author={Chung, Sunghyo and Park, Cheonbok and Suh, Sangho and Kang, Kyeongpil and Choo, Jaegul and Kwon, Bum Chul}, booktitle={Future of interactive learning machines workshop at the 30th annual conference on neural information processing systems (NIPS)}, year={2016} }