arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.00701cs.LGstat.ML
收藏

多层基追踪、有效算法与卷积神经网络

On Multi-Layer Basis Pursuit, Efficient Algorithms and Convolutional Neural Networks

Johns Hopkins University(约翰斯·霍普金斯大学);Technion – Israel Institute of Technology(以色列理工学院);Tel Aviv University(特拉维夫大学)

Jeremias Sulam, Aviad Aberdam, Amir Beck, Michael Elad

摘要:

简约表示在信息建模和处理中无处不在。受最近的多层卷积稀疏编码(ML-CSC)模型的启发,本文将传统的基追踪问题推广到多层环境,在合成和分析稀疏先验之间的共生关系中,在不同的表示层引入类似的稀疏执行惩罚。我们在实践中探索了不同的迭代法来解决这个新问题,并提出了一种新的多层迭代软存储算法(ML-ISTA),以及一个快速版本(ML-FISTA)。我们表明,这些嵌套的一阶算法收敛,在这个意义上,近不动点的函数值可以得到任意接近原问题的解决方案。我们进一步展示了这些算法如何有效地实现特定的递归卷积神经网络(CNN),概括前馈网络,而不引入任何参数。我们提出并分析了不同的架构,从而展开了所提出的追求算法的迭代,包括一个新的学习ML-ISTA,提供了一种构建深度递归CNN的原则性方法。与其他类似的结构不同,这些架构为整个网络整体地展开了全球性的追求。我们在监督学习环境中展示了新兴的结构,在保持参数数量不变的同时,不断提高经典CNN的性能。

英文摘要:

Parsimonious representations are ubiquitous in modeling and processing information. Motivated by the recent Multi-Layer Convolutional Sparse Coding (ML-CSC) model, we herein generalize the traditional Basis Pursuit problem to a multi-layer setting, introducing similar sparse enforcing penalties at different representation layers in a symbiotic relation between synthesis and analysis sparse priors. We explore different iterative methods to solve this new problem in practice, and we propose a new Multi-Layer Iterative Soft Thresholding Algorithm (ML-ISTA), as well as a fast version (ML-FISTA). We show that these nested first order algorithms converge, in the sense that the function value of near-fixed points can get arbitrarily close to the solution of the original problem. We further show how these algorithms effectively implement particular recurrent convolutional neural networks (CNNs) that generalize feed-forward ones without introducing any parameters. We present and analyze different architectures resulting unfolding the iterations of the proposed pursuit algorithms, including a new Learned ML-ISTA, providing a principled way to construct deep recurrent CNNs. Unlike other similar constructions, these architectures unfold a global pursuit holistically for the entire network. We demonstrate the emerging constructions in a supervised learning setting, consistently improving the performance of classical CNNs while maintaining the number of parameters constant.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑