Method and system for linear processing of an input using Gaussian Belief Propagation
AssigneeThe Regents of the University of California
InventorsOri Shental, Danny Dolev, Danny Bickson
Life of this patent
Estimating the term…
Abstract
Methods and systems for processing an input. An input vector y is received that represents a noisy observation of Ax, where A is a data matrix and x is a data vector of unknown variables. Data vector x is recovered from the received input vector y via an iterative method. The recovering comprises determining an inference of a vector of marginal means over a graph G, where the graph G is of a joint Gaussian probability density function p(x) associated with noise in the received input vector y.
Claims32
A processing method comprising:
- receiving an input vector y that represents a noisy observation of Ax, where A is a data matrix and x is a vector of unknown variables;
- recovering x from said received input vector y via an iterative method;
- wherein said recovering comprises determining an inference of a vector of marginal means over a graph G, where the graph G is of a joint Gaussian probability density function p(x) associated with noise in said received input vector y.
A method of processing a signal comprising:
- receiving a signal at an antenna corresponding to an input vector r=Sx+n, where r is an N-length vector of received samples at the antenna, S is an N×K spreading code matrix, x is a message vector, and n is a noise vector;
- filtering said received signal by a matched filter;
- recovering x based on said filtered signal;
- wherein said recovering x comprises determining an inference of a vector of marginal means over a graph G, where the graph G is of a joint Gaussian probability density function p(x) associated with noise in said filtered signal.
A method of processing a signal from l transmitting antennas, the method comprising:
- receiving a signal at m receiving antennas corresponding to an input vector r=Hx+n, where r is an m-length vector of received samples at the m antennas, H is an m×l matrix, x is a message vector, and n is a noise vector;
- filtering said received signal by a matched filter;
- recovering x based on said filtered signal;
- wherein said recovering x comprises determining an inference of a vector of marginal means over a graph g, where the graph g is of a joint Gaussian probability density function p(x) associated with noise in said filtered signal.
Dependencies are inferred from the claim text.