Use of Frequency Domain for Complexity Reduction of Convolutional Neural Networks

The implementation of convolutional neural networks (CNNs) is not easy because of the high number of parameters that these networks have. Researchers have applied numerous approaches to reduce the complexity of convolutional networks. Quantization of the weights and pruning are two complexity reduction methods. A new paradigm for accelerating CNNs operations and simplification of the network is to perform all the computations in the Fourier …