Lessons From Deep Neural Networks for Studying the Coding Principles of Biological Neural Networks
- Authors
- Bae, Hyojin; Kim, Sang Jeong; Kim, Chang-Eop
- Issue Date
- Jan-2021
- Publisher
- Frontiers Media S.A.
- Keywords
- biological neural networks; deep neural networks; neural coding; neural feature; shortcut learning; systems neuroscience
- Citation
- Frontiers in Systems Neuroscience, v.14
- Journal Title
- Frontiers in Systems Neuroscience
- Volume
- 14
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/80008
- DOI
- 10.3389/fnsys.2020.615129
- ISSN
- 1662-5137
- Abstract
- One of the central goals in systems neuroscience is to understand how information is encoded in the brain, and the standard approach is to identify the relation between a stimulus and a neural response. However, the feature of a stimulus is typically defined by the researcher's hypothesis, which may cause biases in the research conclusion. To demonstrate potential biases, we simulate four likely scenarios using deep neural networks trained on the image classification dataset CIFAR-10 and demonstrate the possibility of selecting suboptimal/irrelevant features or overestimating the network feature representation/noise correlation. Additionally, we present studies investigating neural coding principles in biological neural networks to which our points can be applied. This study aims to not only highlight the importance of careful assumptions and interpretations regarding the neural response to stimulus features but also suggest that the comparative study between deep and biological neural networks from the perspective of machine learning can be an effective strategy for understanding the coding principles of the brain. © Copyright © 2021 Bae, Kim and Kim.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 한의과대학 > 한의예과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/80008)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.