arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1310.6536cs.LGq-bio.NCstat.ML
收藏

Randomized co-training:从皮层神经元到机器学习,然后再回来

Randomized co-training: from cortical neurons to machine learning and back again

ETH Zurich(苏黎世联邦理工学院)

David Balduzzi

摘要:

尽管它的大小和复杂性,人类大脑皮层表现出惊人的解剖结构,这表明可能有简单的元算法底层皮层学习和计算。我们希望这样的元算法会引起人们的兴趣,因为它们需要快速,可扩展和有效地运行,几乎没有专门的假设。本文关注的是一个具体的问题:神经元如何使用大量未标记的数据来加速从奖励系统提供的相对罕见的标签中学习?作为部分答案,我们提出随机协同训练作为满足上述要求的生物学上合理的元算法。作为证据,我们描述了一个生物启发的算法,相关的Nystrom视图(XNV),实现了最先进的性能在半监督学习,和草图工作正在进行中的神经元实现。

英文摘要:

Despite its size and complexity, the human cortex exhibits striking anatomical regularities, suggesting there may simple meta-algorithms underlying cortical learning and computation. We expect such meta-algorithms to be of interest since they need to operate quickly, scalably and effectively with little-to-no specialized assumptions. This note focuses on a specific question: How can neurons use vast quantities of unlabeled data to speed up learning from the comparatively rare labels provided by reward systems? As a partial answer, we propose randomized co-training as a biologically plausible meta-algorithm satisfying the above requirements. As evidence, we describe a biologically-inspired algorithm, Correlated Nystrom Views (XNV) that achieves state-of-the-art performance in semi-supervised learning, and sketch work in progress on a neuronal implementation.

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。

↑