In this work, we base on multi-layered perceptron neural networks with backpropagation algorithm (MLPIBP) to construct multi-input multi-output (MIMO) decision feedback equalizers (DFEs). The proposal is used to recover distorted quadrature phaseshift keying (QPSK) signal. From the simulations, we note that the proposed scheme can recover severe distorted signals as well as suppress intersymbol interference (lSI), adjacent charmel interference (ACI) and background additive white Gaussian noise (AWGN). The better bit-error-rate (BER) and packet-error-rate (PER) performance as compared to a set of least-mean-square (LMS) DFEs is achieved. The presented MLPIBP-based MIMO DFE under the severe lSI charmels with ACI and AWGN can improve over 1.5dB at PER=10-1 and BER=10-3.