Factorization Meets the Neighborhood: a MultifacetedCollaborative Filtering Model 阅读笔记
0.奇异值分解SingularValueDecompositionSVD是将一个m×nm\timesnm×n的矩阵分解成三个矩阵的乘积即A=UΣVTA=U\SigmaV^TA=UΣVT其中U,VU,VU,V分别为m×m,n×nnm\timesm,n\timesnnm×m,n×nn的矩阵Σ\SigmaΣ是一个m×nm\timesnm×n的对角矩阵其中UUU,是左奇异矩阵,为AATAA^TAAT的所有