Adaptive filtering techniques using neural networks

An adaptive filter automatically adjusts its own impulse response. In this paper adaptive noise canceller and adaptive signal enhancer systems are implemented using feedforward and recurrent neural networks using back propagation algorithm and real time recurrent learning algorithm respectively for training. Their performances are compared with conventional adaptive filtering techniques using LMS and RLS algorithms. The recurrent neural network employing RTRL algorithm which functions better than the other algorithms is studied further by varying the number of nodes, adding a bias to the neurons, adding a momentum term for learning and varying the momentum term and learning rate for better convergence.