Unbiased reconstruction of nonlinear distortions

When a signal goes through a system having a static, nonlinear transfer function, the output signal will be distorted. In addition, the detected output signal is usually contaminated by noise, due to the noisy environment. If we compensate the nonlinearity with its inverse, the expected value of the output signal will be different from it´s original one, due to the nonlinearly distorted noise. If this difference is not acceptable, we have to use a different compensation function. We show an iterative method, which can produce a unbiased compensation function in the knowledge of the original nonlinear distortion and the noise distribution. The resultant output signal has the same expected value as the original one.