Least Mean Square adaptive filter.

The Least Mean Square adaptive filter is an FIR filter that adapts its coefficients, h[n,i], so that output y[n] most closely matches (in a mean-square sense) a given desired signal d[n] which is the output of another presumed linear time-invariant filter and both filters outputting y[n] and d[n] are driven by a common input, x[n].