基于局部学习规则的子空间分析神经网络
A Neural Network with Local Learning Rules for Minor Subspace Analysis
摘要：
神经形态硬件的发展和生物神经网络的建模需要具有局部学习规则的算法。人工神经网络使用本地学习规则来执行主子空间分析（PSA）和聚类最近已从原则性目标函数。然而，没有生物合理的网络存在的次要子空间分析（MSA），一个基本的信号处理任务。MSA提取输入信号协方差矩阵的最低方差子空间。在这里，我们介绍了一种新的相似性匹配目标提取次要子空间，次要子空间相似性匹配（MSSM）。此外，我们推导出一个自适应MSSM算法，自然映射到一个新的神经网络与本地学习规则，并给出数值结果表明，我们的方法收敛在一个有竞争力的速度。
英文摘要：
The development of neuromorphic hardware and modeling of biological neural networks requires algorithms with local learning rules. Artificial neural networks using local learning rules to perform principal subspace analysis (PSA) and clustering have recently been derived from principled objective functions. However, no biologically plausible networks exist for minor subspace analysis (MSA), a fundamental signal processing task. MSA extracts the lowest-variance subspace of the input signal covariance matrix. Here, we introduce a novel similarity matching objective for extracting the minor subspace, Minor Subspace Similarity Matching (MSSM). Moreover, we derive an adaptive MSSM algorithm that naturally maps onto a novel neural network with local learning rules and gives numerical results showing that our method converges at a competitive rate.
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。
