当前位置:
X-MOL 学术
›
arXiv.cs.ET
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Continual General Chunking Problem and SyncMap
arXiv - CS - Emerging Technologies Pub Date : 2020-06-14 , DOI: arxiv-2006.07853 Danilo Vasconcellos Vargas and Toshitake Asabuki
arXiv - CS - Emerging Technologies Pub Date : 2020-06-14 , DOI: arxiv-2006.07853 Danilo Vasconcellos Vargas and Toshitake Asabuki
Humans possess an inherent ability to chunk sequences into their constituent
parts. In fact, this ability is thought to bootstrap language skills to the
learning of image patterns which might be a key to a more animal-like type of
intelligence. Here, we propose a continual generalization of the chunking
problem (an unsupervised problem), encompassing fixed and probabilistic chunks,
discovery of temporal and causal structures and their continual variations.
Additionally, we propose an algorithm called SyncMap that can learn and adapt
to changes in the problem by creating a dynamic map which preserves the
correlation between variables. Results of SyncMap suggest that the proposed
algorithm learn near optimal solutions, despite the presence of many types of
structures and their continual variation. When compared to Word2vec, PARSER and
MRIL, SyncMap surpasses or ties with the best algorithm on $77\%$ of the
scenarios while being the second best in the remaing $23\%$.
中文翻译:
连续一般分块问题和 SyncMap
人类具有将序列分成组成部分的固有能力。事实上,这种能力被认为可以将语言技能引导到图像模式的学习中,这可能是获得更像动物的智能的关键。在这里,我们提出了对分块问题(无监督问题)的持续概括,包括固定和概率分块、时间和因果结构的发现及其持续变化。此外,我们提出了一种称为 SyncMap 的算法,该算法可以通过创建一个保留变量之间相关性的动态映射来学习和适应问题的变化。SyncMap 的结果表明,尽管存在多种类型的结构及其不断变化,但所提出的算法学习接近最优解。与 Word2vec、PARSER 和 MIL 相比,
更新日期:2020-06-17
中文翻译:
连续一般分块问题和 SyncMap
人类具有将序列分成组成部分的固有能力。事实上,这种能力被认为可以将语言技能引导到图像模式的学习中,这可能是获得更像动物的智能的关键。在这里,我们提出了对分块问题(无监督问题)的持续概括,包括固定和概率分块、时间和因果结构的发现及其持续变化。此外,我们提出了一种称为 SyncMap 的算法,该算法可以通过创建一个保留变量之间相关性的动态映射来学习和适应问题的变化。SyncMap 的结果表明,尽管存在多种类型的结构及其不断变化,但所提出的算法学习接近最优解。与 Word2vec、PARSER 和 MIL 相比,