Reducing Deep Network Complexity with Fourier Transform Methods

12/15/2017
by   Andrew Kiruluta, et al.
0

We propose a novel way that uses shallow densely connected neuron network architectures to achieve superior performance to convolution based neural networks (CNNs) approaches with the added benefits of lower computation burden requiring dramatically less training examples to achieve high prediction accuracy (>98%). The advantages of our proposed method is demonstrated in results on benchmark datasets which show significant performance gain over existing state-of-the-art results on MNIST, CIFAR-10 and CIFAR-100. By Fourier transforming the inputs, each point in the training sample then has a representational energy of all the weighted information from every other point. The consequence of using this input is a reduced complexity neuron network, reduced computation load and the lifting of the requirement for a large number of training examples to achieve high classification accuracy.

READ FULL TEXT

page 4

page 7

research
10/02/2019

A Pre-defined Sparse Kernel Based Convolution for Deep CNNs

The high demand for computational and storage resources severely impede ...
research
01/02/2020

Lightweight Residual Densely Connected Convolutional Neural Network

Extremely efficient convolutional neural network architectures are one o...
research
03/27/2020

Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions

Convolutional neural networks (CNNs) have a large number of variables an...
research
10/02/2019

A Pre-defined Sparse Kernel Based Convolutionfor Deep CNNs

The high demand for computational and storage resources severely impede ...
research
07/12/2021

PonderNet: Learning to Ponder

In standard neural networks the amount of computation used grows with th...
research
07/24/2023

Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs

As deep learning models continue to advance and are increasingly utilize...
research
06/05/2019

Butterfly Transform: An Efficient FFT Based Neural Architecture Design

In this paper, we introduce the Butterfly Transform (BFT), a light weigh...

Please sign up or login with your details

Forgot password? Click here to reset