کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
378662 659182 2006 15 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Are unsupervised neural networks ignorant? Sizing the effect of environmental distributions on unsupervised learning
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
پیش نمایش صفحه اول مقاله
Are unsupervised neural networks ignorant? Sizing the effect of environmental distributions on unsupervised learning
چکیده انگلیسی

Learning environmental biases is a rational behavior: by using prior odds, Bayesian networks rapidly became a benchmark in machine learning. Moreover, a growing body of evidence now suggests that humans are using base rate information. Unsupervised connectionist networks are used in computer science for machine learning and in psychology to model human cognition, but it is unclear whether they are sensitive to prior odds. In this paper, we show that hard competitive learners are unable to use environmental biases while recurrent associative memories use frequency of exemplars and categories independently. Hence, it is concluded that recurrent associative memories are more useful than hard competitive networks to model human cognition and have a higher potential in machine learning.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Cognitive Systems Research - Volume 7, Issue 4, December 2006, Pages 357–371
نویسندگان
, , ,