Analysis of representations of 3D objects in the temporal association area using machine learning
-
- Okamura Jun-ya
- Department of Information Science and Biomedical Engineering, Graduate School of Science and Engineering, Kagoshima University, Kagoshima, Japan
-
- Yamamoto Yusuke
- Department of Information Science and Biomedical Engineering, Graduate School of Science and Engineering, Kagoshima University, Kagoshima, Japan
-
- Dai Lulin
- Department of Information Science and Biomedical Engineering, Graduate School of Science and Engineering, Kagoshima University, Kagoshima, Japan
-
- Yoshihiro Uto
- Department of Information Science and Biomedical Engineering, Faculty of Engineering, Kagoshima University, Kagoshima, Japan
-
- Yousuke Yamada
- Department of Information Science and Biomedical Engineering, Graduate School of Science and Engineering, Kagoshima University, Kagoshima, Japan
-
- Wang Gang
- Department of Information Science and Biomedical Engineering, Graduate School of Science and Engineering, Kagoshima University, Kagoshima, Japan
Bibliographic Information
- Other Title
-
- 機械学習を用いた側頭連合野神経細胞集団における三次元物体の表現の解析
Abstract
<p>We can recognize three-dimensional objects regardless of viewing angles. Previous electrophysiological studies found the cells in the temporal association area responded tolerantly in a certain viewing angle range to the objects experienced in discrimination at the same viewing angles. In the present study, machine learning was applied to response vectors of populations of cells in the temporal association area. A classifier was trained to discriminate the objects within each of experienced viewing angles, and then tested by response vectors to the object images at different viewing angles. The discrimination performance was higher in the objects experienced in discrimination within the same viewing angles than the objects without discrimination experience, and comparable to that in the objects experienced by learning association of different views. The results demonstrate, with the help of recent machine learning techniques applied directly to cellular responses, possible computational model of object representation in the temporal association area.</p>
Journal
-
- Transactions of Japanese Society for Medical and Biological Engineering
-
Transactions of Japanese Society for Medical and Biological Engineering Annual58 (Abstract), 321-321, 2020
Japanese Society for Medical and Biological Engineering
- Tweet
Details 詳細情報について
-
- CRID
- 1390848250134397312
-
- NII Article ID
- 130007885035
-
- ISSN
- 18814379
- 1347443X
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed