Noise cancellation in the field of Adaptive filterinfag has become the essential requirement of the signal processing .The standard multilayer perceptron (MLP) model of Neural Networks is now popular in Adaptive filtering This paper presents the noise-cancellation technique based on Generalized-mean neuron network (GMN). This network consists of an aggregation function, which is based on the generalized mean of all the inputs applied to it. Performance of this GMN network is also compared with traditional MLP networks. The simulation results show the GMN network can be suitably applied for the signal detection.