Adaptive Noise Cancellation Using Deep Cerebellar Model Articulation Controller

Authors:

Abstract
This paper proposes a deep cerebellar model articulation controller (DCMAC) for adaptive noise cancel-lation (ANC). We expand upon the conventional CMAC by stacking single-layer CMAC models into multiple layers to form a DCMAC model, and derive a backpropagation training algorithm to learn the DCMAC parameters. Com-pared with conventional CMAC, the DCMAC can charac-terize nonlinear transformations more effectively because of its deep structure. Experimental results confirm that the proposed DCMAC model outperforms the CMAC in terms of residual noise in an ANC task, showing that DCMAC provides enhanced capability to model channel characteris-tics.
Funding Information
  • Ministry of Science and Technology, Taiwan (MOST 106-2221-E-001-017-MY2, MOST 107-2634-F-155-001)

This publication has 22 references indexed in Scilit: