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 2206.04490cs.LGcs.PF
收藏

深度线性神经网络中的冗余

Redundancy in Deep Linear Neural Networks

Faculty of Math&CS(数学与计算机科学学院);Weizmann Institute of Science(魏茨曼科学研究所)

Oriel BenShmuel

摘要:

传统观点认为,深度线性神经网络受益于单个线性层的表现力和优化优势。本文提出,在实践中,使用传统优化器的深度线性全连接网络的训练过程与单个线性全连接层相同,是凸的。本文旨在解释并证明这一说法。尽管卷积网络与此描述不一致,但这项工作旨在获得对全连接线性网络的新概念理解,这可能会揭示卷积设置和非线性架构的可能约束。

英文摘要:

Conventional wisdom states that deep linear neural networks benefit from expressiveness and optimization advantages over a single linear layer. This paper suggests that, in practice, the training process of deep linear fully-connected networks using conventional optimizers is convex in the same manner as a single linear fully-connected layer. This paper aims to explain this claim and demonstrate it. Even though convolutional networks are not aligned with this description, this work aims to attain a new conceptual understanding of fully-connected linear networks that might shed light on the possible constraints of convolutional settings and non-linear architectures.

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。

↑