Kutrz Kenneth J
Department of Psychology, Binghamton University, Binghamton, New York 13902, USA.
Psychon Bull Rev. 2007 Aug;14(4):560-76. doi: 10.3758/bf03196806.
A novel theoretical approach to human category learning is proposed in which categories are represented as coordinated statistical models of the properties of the members. Key elements of the account are learning to recode inputs as task-constrained principle components and evaluating category membership in terms of model fit-that is, the fidelity of the reconstruction after recoding and decoding the stimulus. The approach is implemented as a computational model called DIVA (for DIVergent Autoencoder), an artificial neural network that uses reconstructive learning to solve N-way classification tasks. DIVA shows good qualitative fits to benchmark human learning data and provides a compelling theoretical alternative to established models.
本文提出了一种全新的人类类别学习理论方法，其中类别被表示为成员属性的协调统计模型。该理论的关键要素包括学习将输入重新编码为任务约束主成分，并根据模型拟合度（即对刺激进行重新编码和解码后的重建保真度）来评估类别成员资格。该方法被实现为一个名为DIVA（发散自编码器）的计算模型，这是一种利用重建学习来解决N路分类任务的人工神经网络。DIVA对基准人类学习数据显示出良好的定性拟合，并为现有模型提供了一种引人注目的理论替代方案。
