Knowledge Commons of Institute of Automation,CAS
Reconstructing Perceived Images from Human Brain Activities with Bayesian Deep Multi-view Learning | |
Du Changde1,2![]() ![]() | |
发表期刊 | IEEE Transactions on Neural Networks and Learning Systems
![]() |
2018 | |
期号 | 0页码:1-14 |
摘要 | Neural decoding, which aims to predict external visual stimuli information from evoked brain activities, plays an important role in understanding human visual system. Many existing methods are based on linear models, and most of them only focus on either the brain activity pattern classification or visual stimuli identification. Accurate reconstruction of the perceived images from the measured human brain activities still remains challenging. In this paper, we propose a novel deep generative multi-view model (DGMM) for the accurate visual image reconstruction from the human brain activities measured by functional magnetic resonance imaging (fMRI). Specifically, we model the statistical relationships between two views (i.e., the visual stimuli and the evoked fMRI) by using two view-specific generators with a shared latent space. On the one hand, we adopt a deep neural network architecture for visual image generation, which mimics the stages of human visual processing. On the other hand, we design a sparse Bayesian linear model for fMRI activity generation, which can effectively capture voxel correlations, suppress data noise and avoid overfitting. Furthermore, we devise an efficient mean-field variational inference method to train the proposed model. The proposed method can accurately reconstruct visual images via Bayesian inference. In particular, we exploit a posterior regularization technique in the Bayesian inference to regularize the model posterior. The quantitative and qualitative evaluations conducted on multiple fMRI datasets demonstrate the proposed method can reconstruct visual images more accurately than the state-of-the-art. |
关键词 | Deep Neural Network Multi-view Learning Variational Bayesian Inference Neural Decoding Image Reconstruction |
语种 | 英语 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23609 |
专题 | 脑图谱与类脑智能实验室_神经计算与脑机交互 |
通讯作者 | He Huiguang |
作者单位 | 1.Research Center for Brain-Inspired Intelligence, Institute of Automation, Chinese Academy of Sciences (CAS), Beijing 100190, China 2.Center for Excellence in Brain Science and Intelligence Technology, CAS, Shanghai 200031, China 3.University of Chinese Academy of Sciences, Beijing 100049, China 4.Laboratory of Parallel Software and Computational Science, Institute of Software, CAS, Beijing 100190, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Du Changde,Du Changying,Huang Lijie,et al. Reconstructing Perceived Images from Human Brain Activities with Bayesian Deep Multi-view Learning[J]. IEEE Transactions on Neural Networks and Learning Systems,2018(0):1-14. |
APA | Du Changde,Du Changying,Huang Lijie,&He Huiguang.(2018).Reconstructing Perceived Images from Human Brain Activities with Bayesian Deep Multi-view Learning.IEEE Transactions on Neural Networks and Learning Systems(0),1-14. |
MLA | Du Changde,et al."Reconstructing Perceived Images from Human Brain Activities with Bayesian Deep Multi-view Learning".IEEE Transactions on Neural Networks and Learning Systems .0(2018):1-14. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
TNNLS_2018_Reconstru(3843KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论