当前位置: X-MOL 学术Inf. Comput. › 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.)
Learners based on transducers
Information and Computation ( IF 0.8 ) Pub Date : 2020-12-15 , DOI: 10.1016/j.ic.2020.104676
Sanjay Jain 1 , Shao Ning Kuek 2 , Eric Martin 3 , Frank Stephan 1, 2
Affiliation  

The learners considered here process data in cycles and maintain as a long term memory a string which provides all internal data the learner can use in the next cycle. Updating of these strings is usually done by either recursive or automatic learners. The present work looks at transduced learners, which sit in-between. The results include that transduced learners can learn all learnable automatic families with memory exponential in the size of the longest input seen so far. Furthermore, there is a hierarchy based on the memory-allowance: if n is the size of the largest datum seen so far, then for all k1, memory nk+1 allows one to learn more automatic families than memory nk. Further results shed light on when it can be imposed that transduced learners be consistent, conservative or iterative. The main result of this kind is that all learnable automatic families have a consistent and conservative transduced learner.



中文翻译:

基于传感器的学习者

这里考虑的学习者循环处理数据,并作为长期记忆维护一个字符串,该字符串提供学习者可以在下一个循环中使用的所有内部数据。这些字符串的更新通常由递归或自动学习器完成。目前的工作着眼于转换学习者,它们介于两者之间。结果包括转导学习器可以学习所有可学习的自动族,其记忆力与迄今为止看到的最长输入的大小呈指数级。此外,还有一个基于内存允许的层次结构:如果n是迄今为止看到的最大数据的大小,那么对于所有ķ1, 记忆nķ+1允许人们学习比记忆更多的自动家庭nķ. 进一步的结果揭示了何时可以强制转换的学习者是一致的、保守的或迭代的。这种类型的主要结果是所有可学习的自动家庭都有一个一致且保守的转导学习器。

更新日期:2020-12-15
down
wechat
bug