When unlearning helps
When unlearning helps
复制标题
当忘却有帮助时
DOI：
10.1016/j.ic.2007.10.005
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
Rolf Wiehagen
中科院分区：
文献类型：
--
作者：
Ganesh Baliga;J. Case;W. Merkle;F. Stephan;Rolf Wiehagen
在儿童语言学习中看到的过度规则化，例如，动词时态结构，涉及放弃正确的行为，以不正确的行为，后来又恢复到正确的行为。相当多的其他儿童发展现象也遵循这种U形的学习、忘却和再学习形式。一个果断的学习者不会这样做，更一般地说，永远不会放弃一个假设H为一个不等价的假设，后来又提出一个等价于H的假设，其中等价意味着语义或行为上的等价。本文的第一个主要结果是，决策性是一个真实的限制黄金的解释性（或在极限）学习语法的语言从积极的数据。这个结果也解决了Osherson，Stob和Weinstein在1986年提出的一个公开问题。第二次决定性学习者对任何语言的每一个假设最多进行两次语义推测。相比之下，这样的学习者不限制黄金的学习模式。非U形学习放宽了对决策性的要求，从限制所有假设输出到同样的限制，但只限于正确的假设。非U型学习的学习力情况比决定性学习的学习力情况要复杂一些。下文对此作了简要说明。Gold最初的模型是从实证数据中学习语法，称为EX学习，成功需要句法收敛到正确的语法。一个轻微的变体，称为BC学习，只需要语义收敛到一系列正确的语法，这些语法不需要在句法上彼此相同。第二个主要结果表明，非U形学习并不限制EX学习。然而，从Fulk，Jain和Osherson的论点来看，非U形学习确实限制了BC学习。在最后一节中讨论了可能的意义，认知科学，这些结果，并在这方面，指出了一些途径值得今后的调查。
Overregularization seen in child language learning, for example, verb tense constructs, involves abandoning correct behaviours for incorrect ones and later reverting to correct behaviours. Quite a number of other child development phenomena also follow this U-shaped form of learning, unlearning and relearning. A decisive learner does not do this and, more generally, never abandons an hypothesis H for an inequivalent one where it later conjectures an hypothesis equivalent to H, where equivalence means semantical or behavioural equivalence. The first main result of the present paper entails that decisiveness is a real restriction on Gold’s model of explanatory (or in the limit) learning of grammars for languages from positive data. This result also solves an open problem posed in 1986 by Osherson, Stob and Weinstein. Second-time decisive learners semantically conjecture each of their hypotheses for any language at most twice. By contrast, such learners are shown not to restrict Gold’s model of learning. Non U-shaped learning liberalizes the requirement of decisiveness from being a restriction on all hypotheses output to the same restriction but only on correct hypotheses. The situation regarding learning power for non U-shaped learning is a little more complex than that for decisiveness. This is explained shortly below. Gold’s original model for learning grammars from positive data, called EX-learning, requires, for success, syntactic convergence to a correct grammar. A slight variant, called BC-learning, requires only semantic convergence to a sequence of correct grammars that need not be syntactically identical to one another. The second main result says that non U-shaped learning does not restrict EX-learning. However, from an argument of Fulk, Jain and Osherson, non U-shaped learning does restrict BC-learning. In the final section is discussed the possible meaning, for cognitive science, of these results and, in this regard, indicated are some avenues worthy of future investigation.
影响因子：
9.5
作者：
G. Marcus;S. Pinker;M. Ullman;Michelle A. Hollander;T. Rosen;Fei Xu;H. Clahsen
通讯作者：
G. Marcus;S. Pinker;M. Ullman;Michelle A. Hollander;T. Rosen;Fei Xu;H. Clahsen