Takane, Y., Oshima-Takane, Y., & Shultz, T. R. (1995). Network analyses: The case of first and second person pronouns. Proceedings of the 1995 IEEE International Conference on Systems, Man and Cybernetics (pp. 3594-3599).



Feed-forward neural network models may be viewed as approximating nonlinear functions connecting inputs to outputs. We analyzed the mechanism of function approximations underlying learning of first and second person pronouns by the cascade-correlation (CC) network The CC network dynamically grows nets to approximate increasingly more complicated functions. It starts as a net without hidden units, but as soon as it “perceives” that it can no longer improve its performance within the limit of current net topology, it automatically recruits a new hidden unit. This process is repeated until a satisfactory degree of function approximation is achieved. Learning of first and second person pronouns presents an interesting problem in psychology. When the mother talks to her child, me refers to herself, and you to the child. However, when the child talks to the mother, me refers to the child, and you to the mother. Learning of the shifting reference of these pronouns can be regarded as a special kind of nonlinear function learning, where the function to be learned stipulates me if the speaker and the referent agree, and you if the addressee and the referent agree. We investigated how this function is approximated by the CC network using graphic techniques. The function approximation typically depends on the sample of input-output patterns used in training, which is called the problem of environmental bias. We examined the effects of environmental bias in two conditions: the addressee condition in which the addressee was always the child, and the nonaddressee condition in which the child was neither the speaker nor the addressee. It was found that exposures to nonaddressee patterns were crucial for networks’ learning of the target function underlying the correct use of pronouns, and that a more variety of nonaddressee patterns facilitate the learning.



Copyright notice

Abstracts, papers, chapters, and other documents are posted on this site as an efficient way to distribute reprints. The respective authors and publishers of these works retain all of the copyrights to this material. Anyone copying, downloading, bookmarking, or printing any of these materials agrees to comply with all of the copyright terms. Other than having an electronic or printed copy for fair personal use, none of these works may be reposted, reprinted, or redistributed without the explicit permission of the relevant copyright holders.


To obtain a PDF reprint of this particular article, signal your agreement with these copyright terms by clicking on the statement below.


I agree with all of these copyright terms PDF 745KB