arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05479eess.SPcs.NEq-bio.NC
收藏

基于局部学习规则的神经网络盲有界源分离

Blind Bounded Source Separation Using Neural Networks with Local Learning Rules

Alper T. Erdogan, Cengiz Pehlevan

摘要:

自然信号处理系统和工程信号处理系统所遇到的一个重要问题是盲源分离。在这个问题的许多实例中,源被它们的性质所限制,并且是已知的,即使特定的界限可能是未知的。为了将这些有界源从它们的混合物中分离出来,我们提出了一个新的优化问题,有界相似匹配(BSM)。一个自适应BSM算法的原理推导导致一个具有限幅非线性的递归神经网络。该网络适应当地的学习规则,满足了一个重要的约束,在神经形态硬件的生物兼容性和可实施性。

英文摘要:

An important problem encountered by both natural and engineered signal processing systems is blind source separation. In many instances of the problem, the sources are bounded by their nature and known to be so, even though the particular bound may not be known. To separate such bounded sources from their mixtures, we propose a new optimization problem, Bounded Similarity Matching (BSM). A principled derivation of an adaptive BSM algorithm leads to a recurrent neural network with a clipping nonlinearity. The network adapts by local learning rules, satisfying an important constraint for both biological plausibility and implementability in neuromorphic hardware.

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。

↑