Discrete Fourier transforms provide a significant speedup in the computation of convolutions
in deep learning. In this work, we demonstrate that, beyond its advantages for efficient …

Recent researches have shown that spectral representation provides a significant speed-up
in the massive computation workload of convolution operations in the inference (feed …

Abstract Filters in a Convolutional Neural Network (CNN) contain model parameters learned
from enormous amounts of data. In this paper, we suggest to decompose convolutional …

Convolutional neural networks (CNNs) are currently state-of-the-art for various classification
tasks, but are computationally expensive. Propagating through the convolutional layers is …

Convoulutional Neural Networks (CNNs) exhibit extraordinary performance on a variety of
machine learning tasks. However, their mathematical properties and behavior are quite …

The convolutional layers are core building blocks of neural network architectures. In general,
a convolutional filter applies to the entire frequency spectrum of the input data. We explore …

Vanilla convolutions in modern deep networks are known to operate locally and at fixed
scale (eg, the widely-adopted 3* 3 kernels in image-oriented tasks). This causes low efficacy …

Background: It is still an open research area to theoretically understand why Deep Neural
Networks (DNNs)---equipped with many more parameters than training data and trained by …

Are neural networks biased toward simple functions? Does depth always help learn more
complex features? Is training the last layer of a network as good as training all layers? How …

Recent success in training deep neural networks have prompted active investigation into the
features learned on their intermediate layers. Such research is difficult because it requires …