arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.07802cs.LGcs.AIcs.NEstat.ML
收藏

局部传播网络学习

Network Learning with Local Propagation

University of Geneva(日内瓦大学)

Dimche Kostadinov, Behrooz Razeghi, Sohrab Ferdowsi, Slava Voloshynovskiy

摘要:

本文提出了一种具有局部传播的局部解耦网络参数学习方法。考虑三个元素:(i)描述所有节点处的表示的非线性变换的集合,(ii)与对应的局部表示目标相关的每个节点处的局部目标,以及(iii)将每个节点处的非线性误差向量与来自直接连接的节点的目标误差向量相关的局部传播模型。建模概念(i),(ii)和(iii)提供了几个优点,包括(a)表示为图的任何网络的统一学习原理,(b)理解和解释局部和全局学习动态,(c)解耦和并行参数学习,(d)在无限长,多路径和多目标网络中学习的可能性。数值实验验证了学习原理的潜力。初步结果表明,在比较国家的最先进的方法,w.r.t.学习时间和网络规模,同时具有相当的识别精度。

英文摘要:

This paper presents a locally decoupled network parameter learning with local propagation. Three elements are taken into account: (i) sets of nonlinear transforms that describe the representations at all nodes, (ii) a local objective at each node related to the corresponding local representation goal, and (iii) a local propagation model that relates the nonlinear error vectors at each node with the goal error vectors from the directly connected nodes. The modeling concepts (i), (ii) and (iii) offer several advantages, including (a) a unified learning principle for any network that is represented as a graph, (b) understanding and interpretation of the local and the global learning dynamics, (c) decoupled and parallel parameter learning, (d) a possibility for learning in infinitely long, multi-path and multi-goal networks. Numerical experiments validate the potential of the learning principle. The preliminary results show advantages in comparison to the state-of-the-art methods, w.r.t. the learning time and the network size while having comparable recognition accuracy.

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。

↑