PhaseDNN - A Parallel Phase Shift Deep Neural Network for Adaptive Wideband Learning
share
In this paper, we propose a phase shift deep neural network (PhaseDNN) which will provide a wideband convergence in approximating a target function during its training of the network. The PhaseDNN utilizes the fact that many DNN achieves convergence in the low frequency range first, thus, a series of moderately-sized of DNNs are constructed and trained in parallel for ranges of higher frequencies. With the help of phase shifts in the frequency domain, through a simple phase factor multiplication on the training data, each DNN in the series will be trained to approximate the target function over a higher range of frequency range. In totality, the proposed PhaseDNN system is able to convert wideband frequency learning to low frequency learning, thus allowing a uniform learning to wideband target functions as well as spatial and frequency adaptive training.
READ FULL TEXT
