skip to main content
Ngôn ngữ:
Giới hạn tìm kiếm: Giới hạn tìm kiếm: Dạng tài nguyên Hiển thị kết quả với: Hiển thị kết quả với: Chỉ mục

Localizing the latent structure canonical uncertainty: entropy profiles for hidden Markov models

Durand, Jean-Baptiste ; Guédon, Yann; Godin, Christophe (Editor)

Statistics and computing, January 2016, Vol.26(1), pp.549-567 [Tạp chí có phản biện]

ISSN: 0960-3174 ; E-ISSN: 1573-1375 ; DOI: 10.1007/s11222-014-9494-9

Truy cập trực tuyến

Trích dẫn Trích dẫn bởi
  • Nhan đề:
    Localizing the latent structure canonical uncertainty: entropy profiles for hidden Markov models
  • Tác giả: Durand, Jean-Baptiste ; Guédon, Yann
  • Godin, Christophe (Editor)
  • Chủ đề: Mathematics ; Statistics ; Computer Science ; Modeling and Simulation ; Hidden Markov Tree Model ; Conditional Entropy ; Plant Structure Analysis ; Hidden Markov Chain Model ; Statistics ; Computer Science ; Mathematics
  • Là 1 phần của: Statistics and computing, January 2016, Vol.26(1), pp.549-567
  • Mô tả: This paper addresses state inference for hidden Markov models. These models rely on unobserved states, which often have a meaningful interpretation. This makes it necessary to develop diagnostic tools for quantification of state uncertainty. The entropy of the state sequence that explains an observed sequence for a given hidden Markov chain model can be considered as the canonical measure of state sequence uncertainty. This canonical measure of state sequence uncertainty is not reflected by the classic multidimensional posterior state (or smoothed) probability profiles because of the marginalization that is intrinsic in the computation of these posterior probabilities. Here, we introduce a new type of profiles that have the following properties: (i) these profiles of conditional entropies are a decomposition of the canonical measure of state sequence uncertainty along the sequence and makes it possible to localise this uncertainty, (ii) these profiles are unidimensional and...
  • Ngôn ngữ: English
  • Số nhận dạng: ISSN: 0960-3174 ; E-ISSN: 1573-1375 ; DOI: 10.1007/s11222-014-9494-9

Đang tìm Cơ sở dữ liệu bên ngoài...