L1 Regularization based Learning Method for Capsule Network
-
- OHTA Nozomu
- University of Tsukuba
-
- KAWAI Shin
- University of Tsukuba
-
- NOBUHARA Hajime
- University of Tsukuba
Bibliographic Information
- Other Title
-
- L1正則化を用いたCapsule Networkの学習法の一提案
Description
<p>Capsule Network is a new neural network proposed to overcome the shortcomings of CNN. However, the Capsule Network has many learnable parameters and is prone to over- tting. In this research, we aim to improve general- ization ability by reducing parameters using L1 regularization. We evaluate our method by comparing the accuracy and the reconstructed image with the conventional method.</p>
Journal
-
- Proceedings of the Annual Conference of JSAI
-
Proceedings of the Annual Conference of JSAI JSAI2019 (0), 1Q3J201-1Q3J201, 2019
The Japanese Society for Artificial Intelligence
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390564238096800128
-
- NII Article ID
- 130007658336
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed