Simple recurrent networks can distinguish non-occurring from ungrammatical sentences given appropriate task structure: reply to Marcus
暂无分享,去创建一个
[1] J. Elman. Distributed Representations, Simple Recurrent Networks, And Grammatical Structure , 1991 .
[2] J. Elman. Learning and development in neural networks: the importance of starting small , 1993, Cognition.
[3] G. Marcus. Can connectionism save constructivism? , 1998, Cognition.
[4] Peter M. Vishton,et al. Rule learning by seven-month-old infants. , 1999, Science.
[5] Douglas L. T. Rohde,et al. Language acquisition in the absence of explicit negative evidence: how important is starting small? , 1999, Cognition.
[6] D. Plaut,et al. Does generalization in infant learning implicate abstract algebra-like rules? , 1999, Trends in Cognitive Sciences.
[7] Z. Dienes,et al. Rule learning by seven-month-old infants and neural networks , 1999 .
[8] R. Gómez,et al. Artificial grammar learning by 1-year-olds leads to specific and abstract knowledge , 1999, Cognition.
[9] G. Marcus. The Algebraic Mind: Integrating Connectionism and Cognitive Science , 2001 .