Computing Gaussian mixture models with EM using equivalence constraints

Noam Shental, Aharon Bar-Hillel, Tomer Hertz, Daphna Weinshall

نتاج البحث: فصل من :كتاب / تقرير / مؤتمرمنشور من مؤتمرمراجعة النظراء

ملخص

Density estimation with Gaussian Mixture Models is a popular generative technique used also for clustering. We develop a framework to incorporate side information in the form of equivalence constraints into the model estimation procedure. Equivalence constraints are defined on pairs of data points, indicating whether the points arise from the same source (positive constraints) or from different sources (negative constraints). Such constraints can be gathered automatically in some learning problems, and are a natural form of supervision in others. For the estimation of model parameters we present a closed form EM procedure which handles positive constraints, and a Generalized EM procedure using a Markov net which handles negative constraints. Using publicly available data sets we demonstrate that such side information can lead to considerable improvement in clustering tasks, and that our algorithm is preferable to two other suggested methods using the same type of side information.

اللغة الأصليةالإنجليزيّة
عنوان منشور المضيفAdvances in Neural Information Processing Systems 17 - Proceedings of the 2003 Conference, NIPS 2003
ناشرNeural information processing systems foundation
رقم المعيار الدولي للكتب (المطبوع)0262201526, 9780262201520
حالة النشرنُشِر - 2004
منشور خارجيًانعم
الحدث17th Annual Conference on Neural Information Processing Systems, NIPS 2003 - Vancouver, BC, كندا
المدة: ٨ ديسمبر ٢٠٠٣١٣ ديسمبر ٢٠٠٣

سلسلة المنشورات

الاسمAdvances in Neural Information Processing Systems
رقم المعيار الدولي للدوريات (المطبوع)1049-5258

!!Conference

!!Conference17th Annual Conference on Neural Information Processing Systems, NIPS 2003
الدولة/الإقليمكندا
المدينةVancouver, BC
المدة٨/١٢/٠٣١٣/١٢/٠٣

قم بذكر هذا