本頁只刊出中文翻譯與中文說明；英文原文請見下方原文連結。
原文連結
論文資訊
- 類型：已發表論文
- 日期：2011
摘要
We improve recently published results about resources of restricted Boltzmann machines (RBM) and deep belief 網絡s (DBN) required to make them universal approximators. We show that any distribution p on the set {0, 1}(n) of binary vectors of length n can be arbitrarily well approximated by an RBM with k - 1 hidden units, where k is the minimal number of pairs of binary vectors differing in only one entry such that their union contains the support set of p. In important cases this number is half the cardinality of the support set of p (given in Le Roux & Bengio, 2008). We construct a DBN with 2(n)/2(n-b), b similar to log n, hidden layers of width n that is capable of approximating any distribution on {0, 1}(n) arbitrarily well. This confirms a conjecture presented in Le Roux and Bengio (2010
※ 此為已發表論文，全文需透過期刊付費取得