Building Compact and Robust Deep Neural Networks with Toeplitz Matrices

09/02/2021
by   Alexandre Araujo, et al.
0

Deep neural networks are state-of-the-art in a wide variety of tasks, however, they exhibit important limitations which hinder their use and deployment in real-world applications. When developing and training neural networks, the accuracy should not be the only concern, neural networks must also be cost-effective and reliable. Although accurate, large neural networks often lack these properties. This thesis focuses on the problem of training neural networks which are not only accurate but also compact, easy to train, reliable and robust to adversarial examples. To tackle these problems, we leverage the properties of structured matrices from the Toeplitz family to build compact and secure neural networks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

01/29/2019

On the Expressive Power of Deep Fully Circulant Neural Networks

In this paper, we study deep fully circulant neural networks, that is de...
09/19/2020

SecDD: Efficient and Secure Method for Remotely Training Neural Networks

We leverage what are typically considered the worst qualities of deep le...
10/14/2019

DeepSearch: Simple and Effective Blackbox Fuzzing of Deep Neural Networks

Although deep neural networks have been successful in image classificati...
04/28/2017

Parseval Networks: Improving Robustness to Adversarial Examples

We introduce Parseval networks, a form of deep neural networks in which ...
05/22/2019

Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspection

Despite having excellent performances for a wide variety of tasks, moder...
05/05/2020

Predicting atmospheric optical properties for radiative transfer computations using neural networks

The radiative transfer equations are well-known, but radiation parametri...
06/22/2018

Compact Deep Neural Networks for Computationally Efficient Gesture Classification From Electromyography Signals

Machine learning classifiers using surface electromyography are importan...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.