arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.01674cs.LGstat.ML
收藏

概率规则的实现与选择

Probabilistic Rule Realization and Selection

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Michigan(密歇根大学)

Haizi Yu, Tianxi Li, Lav R. Varshney

摘要:

抽象和实现是双向的过程,是获得智力和创造力的关键。在许多领域,这两个过程是通过规则来实现的:高级原则,揭示了相似但不同的例子中的不变性。在离散输入空间的概率设置下,我们专注于规则实现问题,该问题生成遵循给定规则的输入样本分布。更雄心勃勃的是,我们超越了机械的实现,接受任何给定的东西,而是要求主动选择合理的规则来实现。这一目标在实践中要求很高,因为初始规则集可能并不总是一致的,因此需要明智的妥协。我们制定的规则实现和选择作为两个强连接的组件在一个单一的和对称的双凸问题,并推导出一个有效的算法,在大规模的工作。以音乐创作规则为例,我们证明了我们的模型的效率,不仅在音乐实现(组成),而且音乐的解释和理解(分析)。

英文摘要:

Abstraction and realization are bilateral processes that are key in deriving intelligence and creativity. In many domains, the two processes are approached through rules: high-level principles that reveal invariances within similar yet diverse examples. Under a probabilistic setting for discrete input spaces, we focus on the rule realization problem which generates input sample distributions that follow the given rules. More ambitiously, we go beyond a mechanical realization that takes whatever is given, but instead ask for proactively selecting reasonable rules to realize. This goal is demanding in practice, since the initial rule set may not always be consistent and thus intelligent compromises are needed. We formulate both rule realization and selection as two strongly connected components within a single and symmetric bi-convex problem, and derive an efficient algorithm that works at large scale. Taking music compositional rules as the main example throughout the paper, we demonstrate our model's efficiency in not only music realization (composition) but also music interpretation and understanding (analysis).

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。

↑