Presentation information

General Session

General Session » J-12 Human interface, education aid

[3M1-GS-12] Human interface, education aid: Online education

Thu. Jun 11, 2020 9:00 AM - 10:40 AM Room M (jsai2020online-13)


9:40 AM - 10:00 AM

[3M1-GS-12-03] Feature Extraction of Students and Problems via Exam Result Analysis using Variational Autoencoder

〇Takashi Hattori1, Hiroshi Sawada1, Takako Tonooka2, Takeshi Sakata2, Sanae Fujita1, Tessei Kobayashi1, Koji Kamei1, Futoshi Naya1 (1. NTT Communication Science Laboratories, 2. Tokyo Shoseki Co.,Ltd.)

Keywords:Students' exam result analysis, Autoencoder, Feature extraction

In this paper, we propose a novel examination-result analysis method based on latent variables gained from
Variational AutoEncoder (VAE) specially designed for this purpose. We train our VAE so that the range of
latent variables are within 0 and 1 and also monotonical concerning output of VAE’s decoder, while minimizing
reconstruction loss between input and output like existing VAEs. Using the latent variables, we report a detailed
analysis of both the problems and the examinee.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.