Active Learning on Neural Networks through Interactive Generation of Digit Patterns and Visual Representation

TL;DR

This paper introduces an interactive system that visualizes and generates digit patterns to enhance understanding of neural networks through real-time recognition and visualization, aiming to improve user learning and interpretability.

Contribution

It presents a novel interactive visualization tool that generates and recognizes digit patterns in real time, aiding user comprehension of neural network operations.

Findings

System improves user understanding of neural network behavior

Visualization helps distinguish digit patterns effectively

User testing indicates high usability and engagement

Abstract

Artificial neural networks (ANNs) have been broadly utilized to analyze various data and solve different domain problems. However, neural networks (NNs) have been considered a black box operation for years because their underlying computation and meaning are hidden. Due to this nature, users often face difficulties in interpreting the underlying mechanism of the NNs and the benefits of using them. In this paper, to improve users' learning and understanding of NNs, an interactive learning system is designed to create digit patterns and recognize them in real time. To help users clearly understand the visual differences of digit patterns (i.e., 0 ~ 9) and their results with an NN, integrating visualization is considered to present all digit patterns in a two-dimensional display space with supporting multiple user interactions. An evaluation with multiple datasets is conducted to determine its usability for active learning. In addition, informal user testing is managed during a summer workshop by asking the workshop participants to use the system.