کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
4945278 1438416 2017 16 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Hierarchical models as marginals of hierarchical models
ترجمه فارسی عنوان
مدل های سلسله مراتبی به عنوان حاشیه های مدل های سلسله مراتبی
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
چکیده انگلیسی
We investigate the representation of hierarchical models in terms of marginals of other hierarchical models with smaller interactions. We focus on binary variables and marginals of pairwise interaction models whose hidden variables are conditionally independent given the visible variables. In this case the problem is equivalent to the representation of linear subspaces of polynomials by feedforward neural networks with soft-plus computational units. We show that every hidden variable can freely model multiple interactions among the visible variables, which allows us to generalize and improve previous results. In particular, we show that a restricted Boltzmann machine with [2(log⁡(v)+1)/(v+1)]2v−1 hidden binary variables can approximate every distribution of v visible binary variables arbitrarily well, which improves the previous bound 2v−1−1.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: International Journal of Approximate Reasoning - Volume 88, September 2017, Pages 531-546
نویسندگان
, ,