Amongst the various classes of adaptive equalizers are the blinds equalizers, which do not require the transmission of a reference signal to the receiver in order to calculate the coefficients. Blind equalizers minimize the problem of ISI using observation of the output signal of the communication channel, together with certain a priori information concerning the statistical properties of the transmitted signal. The fact that no reference signal is used increases the data transmission capacity in systems employing blind equalization. A variety of techniques can be used for the adaptation (or optimization) of the coefficients of the blind equalizer, and one of the most widely used is the gradient descent optimization method known as the constant modulus algorithm (CMA). Nonetheless, the optimization function of the CMA does not provide full convergence, and presents undesirable local minima hat can lead to inefficient reduction of ISI .