连续一般组块问题与SyncMap
Continual General Chunking Problem and SyncMap
摘要:
人类拥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引导语言技能和图像模式的学习,这可能是获得更像动物的智能的关键。在这里,我们提出了一个不断推广的组块问题(无监督的问题),包括固定和概率块,发现时间和因果结构及其不断变化。此外,我们提出了一个算法称为SyncMap,可以学习和适应的问题,通过创建一个动态的地图,保持变量之间的相关性的变化。SyncMap的结果表明,该算法学习接近最优的解决方案,尽管存在许多类型的结构和它们的不断变化。与Word2vec、PARSER和MRIL相比,SyncMap超过或与$66\%$上的最佳算法并列,同时在其余$34\%$中排名第二。SyncMap的无模型简单动力学和损失函数的缺失表明,也许令人惊讶的是,单凭自组织就可以做很多事情。代码可在https://github.com/zweifel/SyncMap获得。
英文摘要:
Humans possess an inherent ability to chunk sequences into their constituent parts. In fact, this ability is thought to bootstrap language skills and 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 $66\%$ of the scenarios while being the second best in the remaining $34\%$. SyncMap's model-free simple dynamics and the absence of loss functions reveal that, perhaps surprisingly, much can be done with self-organization alone. Code available at https://github.com/zweifel/SyncMap.
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。