منابع مشابه
Underestimate Sequences via Quadratic Averaging
In this work we introduce the concept of an Underestimate Sequence (UES), which is a natural extension of Nesterov’s estimate sequence [16]. Our definition of a UES utilizes three sequences, one of which is a lower bound (or under-estimator) of the objective function. The question of how to construct an appropriate sequence of lower bounds is also addressed, and we present lower bounds for stro...
متن کاملTongue motion averaging from contour sequences.
In this paper, a method to get the best representation of a speech motion from several repetitions is presented. Each repetition is a representation of the same speech captured at different times by sequence of ultrasound images and is composed of a set of 2D spatio-temporal contours. These 2D contours in different repetitions are time aligned first by a shape based Dynamic Programming (DP) met...
متن کاملImproved Classification Using Hidden Markov Averaging from Multiple Observation Sequences
The enormous popularity of Hidden Markov models (HMMs) in spatio-temporal pattern recognition is largely due to the ability to “learn” model parameters from observation sequences through the Baum-Welch and other re-estimation procedures. In this study, HMM parameters are estimated from an ensemble of models trained on individual observation sequences. The proposed methods are shown to provide s...
متن کاملAveraging Sequences and Abelian Rank in Amenable Groups
We investigate the connection between the abelian rank of a countable amenable group and the existence of good averaging sequences (eg for the ergodic theorem). We show that if G is a group with finite abelian rank r(G), then 2 is a lower bound on the constant associated to a Tempel’man sequence, and if G is abelain there is a Tempel’man sequence in G with this constant. On the other hand, infi...
متن کاملApplication of DTW Barycenter Averaging to Finding EEG Consensus Sequences
DTW Barycenter Averaging (DBA) has proven to be a useful tool for calculating consensus sequences, but it has not yet been applied to real electroencephalography (EEG) data. This study tests DBA on real EEG sequences using the modification proposed by Kotas et al. (2015), and proposes several further modifications to the initial sequence selection process to improve the method’s efficacy for EE...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Pacific Journal of Mathematics
سال: 2012
ISSN: 0030-8730,0030-8730
DOI: 10.2140/pjm.2012.255.1