XMAP: Programming Memristor Crossbars for Analog Matrix-Vector Multiplication: Toward High Precision Using Representable Matrices.
Necati UysalBaogang ZhangSumit Kumar JhaRickard EwetzPublished in: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. (2022)
Keyphrases
- high precision
- sparse matrix
- matrix multiplication
- eigenvalues and eigenvectors
- matrix representation
- symmetric matrices
- rows and columns
- quantum mechanics
- high recall
- singular value decomposition
- linear algebra
- coefficient matrix
- floating point
- symmetric matrix
- singular values
- square matrices
- positive definite
- covariance matrix
- correlation matrix
- data matrix
- projection matrices
- high reliability
- projection matrix
- positive semidefinite
- perturbation theory
- linear complementarity problem
- pseudo inverse
- achieve high precision
- successive approximation
- low rank and sparse
- totally unimodular
- low rank approximation
- adjacency matrix
- high accuracy
- matrix completion
- distance matrix
- semidefinite
- systems of linear equations
- matrix factorization
- particle swarm optimization
- search space
- decision making