English
Related papers

Related papers: Deep Neural Networks with Trainable Activations an…

200 papers

This paper explores the expressive power of deep neural networks through the framework of function compositions. We demonstrate that the repeated compositions of a single fixed-size ReLU network exhibit surprising expressive power, despite…

Machine Learning · Computer Science 2023-08-01 Shijun Zhang , Jianfeng Lu , Hongkai Zhao

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges. Unfortunately, they are susceptible to various types of noise, including adversarial attacks and corrupted inputs. In this work we…

Machine Learning · Computer Science 2019-09-12 Carlos Lassance , Vincent Gripon , Jian Tang , Antonio Ortega

This article provides a comprehensive understanding of optimization in deep learning, with a primary focus on the challenges of gradient vanishing and gradient exploding, which normally lead to diminished model representational ability and…

Machine Learning · Computer Science 2023-11-14 Xianbiao Qi , Jianan Wang , Lei Zhang

We analyze multi-layer neural networks in the asymptotic regime of simultaneously (A) large network sizes and (B) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the…

Probability · Mathematics 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos

We develop a weak adversarial approach to solving obstacle problems using neural networks. By employing (generalised) regularised gap functions and their properties we rewrite the obstacle problem (which is an elliptic variational…

Optimization and Control · Mathematics 2024-11-28 Amal Alphonse , Michael Hintermüller , Alexander Kister , Chin Hang Lun , Clemens Sirotenko

In this note we consider setups in which variational objectives for Bayesian neural networks can be computed in closed form. In particular we focus on single-layer networks in which the activation function is piecewise polynomial (e.g.…

Machine Learning · Statistics 2018-12-04 Martin Jankowiak

A dynamical neural network consists of a set of interconnected neurons that interact over time continuously. It can exhibit computational properties in the sense that the dynamical system's evolution and/or limit points in the associated…

Machine Learning · Computer Science 2018-05-24 Tsung-Han Lin , Ping Tak Peter Tang

In this paper we consider PIDEs with gradient-independent Lipschitz continuous nonlinearities and prove that deep neural networks with ReLU activation function can approximate solutions of such semilinear PIDEs without curse of…

Numerical Analysis · Mathematics 2025-01-22 Ariel Neufeld , Tuan Anh Nguyen , Sizhou Wu

In this paper, we introduce "Power Linear Unit" (PoLU) which increases the nonlinearity capacity of a neural network and thus helps improving its performance. PoLU adopts several advantages of previously proposed activation functions.…

Machine Learning · Computer Science 2018-02-02 Yikang Li , Pak Lun Kevin Ding , Baoxin Li

Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit. Given the finite size of realistic DNN, we utilize the large deviation theory and path integral analysis to study the deviation…

Disordered Systems and Neural Networks · Physics 2020-02-21 Bo Li , David Saad

In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Idan Kligvasser , Tamar Rott Shaham , Tomer Michaeli

In this article we present new results on neural networks with linear threshold activation functions. We precisely characterize the class of functions that are representable by such neural networks and show that 2 hidden layers are…

Machine Learning · Computer Science 2023-10-20 Sammy Khalife , Hongyu Cheng , Amitabh Basu

Lipschitz constants are connected to many properties of neural networks, such as robustness, fairness, and generalization. Existing methods for computing Lipschitz constants either produce relatively loose upper bounds or are limited to…

Machine Learning · Computer Science 2022-10-17 Zhouxing Shi , Yihan Wang , Huan Zhang , Zico Kolter , Cho-Jui Hsieh

This paper presents the Robust Recurrent Deep Network (R2DN), a scalable parameterization of robust recurrent neural networks for machine learning and data-driven control. We construct R2DNs as a feedback interconnection of a linear…

Machine Learning · Computer Science 2025-04-03 Nicholas H. Barbara , Ruigang Wang , Ian R. Manchester

We consider the approximation rates of shallow neural networks with respect to the variation norm. Upper bounds on these rates have been established for sigmoidal and ReLU activation functions, but it has remained an important open problem…

Machine Learning · Statistics 2021-09-10 Jonathan W. Siegel , Jinchao Xu

It has been widely assumed that a neural network cannot be recovered from its outputs, as the network depends on its parameters in a highly nonlinear way. Here, we prove that in fact it is often possible to identify the architecture,…

Machine Learning · Computer Science 2020-02-25 David Rolnick , Konrad P. Kording

Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations…

Image and Video Processing · Electrical Eng. & Systems 2024-08-05 Joseph Shenouda , Yamin Zhou , Robert D. Nowak

In this effort, we derive a formula for the integral representation of a shallow neural network with the ReLU activation function. We assume that the outer weighs admit a finite $L_1$-norm with respect to Lebesgue measure on the sphere. For…

Machine Learning · Computer Science 2020-06-12 Armenak Petrosyan , Anton Dereventsov , Clayton Webster

Neural networks with piecewise linear activation functions, such as rectified linear units (ReLU) or maxout, are among the most fundamental models in modern machine learning. We make a step towards proving lower bounds on the size of such…

Combinatorics · Mathematics 2026-05-29 Christoph Hertrich , Georg Loho

Applying neural networks as controllers in dynamical systems has shown great promises. However, it is critical yet challenging to verify the safety of such control systems with neural-network controllers in the loop. Previous methods for…

Systems and Control · Electrical Eng. & Systems 2019-06-26 Chao Huang , Jiameng Fan , Wenchao Li , Xin Chen , Qi Zhu
‹ Prev 1 8 9 10 Next ›