|
Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >
Extending Binary Neural Networks to Bayesian Neural Networks with Probabilistic Interpretation of Binary Weights
| Title: | Extending Binary Neural Networks to Bayesian Neural Networks with Probabilistic Interpretation of Binary Weights |
| Authors: | Saito, Taisei Browse this author | | Ando, Kota Browse this author →KAKEN DB | | Asai, Tetsuya Browse this author →KAKEN DB |
| Keywords: | Bayseian neural network | | Binary connect | | quantization | | memory reduction | | uncertainty estimation |
| Issue Date: | 1-Aug-2024 |
| Publisher: | IEICE - Institute of the Electronics, Information and Communication Engineers |
| Journal Title: | IEICE transactions on information and systems |
| Volume: | E107D |
| Issue: | 8 |
| Start Page: | 949 |
| End Page: | 957 |
| Publisher DOI: | 10.1587/transinf.2023LOP0009 |
| Abstract: | Neural networks (NNs) fail to perform well or make excessive predictions when predicting out-of-distribution or unseen datasets. In contrast, Bayesian neural networks (BNNs) can quantify the uncertainty of their inference to solve this problem. Nevertheless, BNNs have not been widely adopted owing to their increased memory and computational cost. In this study, we propose a novel approach to extend binary neural networks by introducing a probabilistic interpretation of binary weights, effectively converting them into BNNs. The proposed approach can reduce the number of weights by half compared to the conventional method. A comprehensive comparative analysis with established methods like Monte Carlo dropout and Bayes by backprop was performed to assess the performance and capabilities of our proposed technique in terms of accuracy and capturing uncertainty. Through this analysis, we aim to provide insights into the advantages of this Bayesian extension. |
| Rights: | Copyright ©2024 The Institute of Electronics, Information and Communication Engineers | | https://search.ieice.org/ |
| Type: | article |
| URI: | http://hdl.handle.net/2115/93033 |
| Appears in Collections: | 情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
Submitter: 浅井 哲也
|
