Latent Tree Approximation in Linear Model

Autor:	Navid Tafaghodi Khajavi
Rok vydání:	2017
Předmět:	FOS: Computer and information sciences 060102 archaeology Computer science Model selection Computer Science - Information Theory Information Theory (cs.IT) Linear model Approximation algorithm 020206 networking & telecommunications 06 humanities and the arts 02 engineering and technology Minimum spanning tree Data modeling Tree (data structure) Tree structure Expectation–maximization algorithm 0202 electrical engineering electronic engineering information engineering 0601 history and archaeology Algorithm
Zdroj:	ICASSP
DOI:	10.48550/arxiv.1710.01838
Popis:	We consider the problem of learning underlying tree structure from noisy, mixed data obtained from a linear model. To achieve this, we use the expectation maximization algorithm combined with Chow-Liu minimum spanning tree algorithm. This algorithm is sub-optimal, but has low complexity and is applicable to model selection problems through any linear model.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b511abba671be67e482bd7c373bb652 Zobrazit plný text záznamu