An interpretable bi-branch neural network for matrix completion

Signal Processing(2022)

引用 1|浏览3
暂无评分
摘要
•We construct a bi-branch neural network for matrix completion.•The proposed neural network is designed via unfolding the matrix factorization formulation and learned by end-to-end training using all individual observed entries.•The developed BiBNN has been applied to image inpainting and recommender system, achieving better performance than state-of-the-art approaches in terms of prediction accuracy.
更多
查看译文
关键词
Low rank,Nonlinear matrix completion,Neural network,Image inpainting,Recommender system
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要