Adaptive Noise Cancellation Using Deep Cerebellar Model Articulation Controller
For researchers in adaptive noise cancellation, this work offers an incremental improvement by deepening an existing neural network architecture.
The paper introduces a deep cerebellar model articulation controller (DCMAC) for adaptive noise cancellation, which stacks multiple CMAC layers and uses a modified backpropagation algorithm. Experiments show DCMAC outperforms conventional CMAC in reducing residual noise.
This paper proposes a deep cerebellar model articulation controller (DCMAC) for adaptive noise cancellation (ANC). We expand upon the conventional CMAC by stacking sin-gle-layer CMAC models into multiple layers to form a DCMAC model and derive a modified backpropagation training algorithm to learn the DCMAC parameters. Com-pared with conventional CMAC, the DCMAC can characterize nonlinear transformations more effectively because of its deep structure. Experimental results confirm that the pro-posed DCMAC model outperforms the CMAC in terms of residual noise in an ANC task, showing that DCMAC provides enhanced modeling capability based on channel characteristics.