English
Related papers

Related papers: Comparative Analysis of Polynomial and Rational Ap…

200 papers

This study explores the number of neurons required for a Rectified Linear Unit (ReLU) neural network to approximate multivariate monomials. We establish an exponential lower bound on the complexity of any shallow network approximating the…

Machine Learning · Computer Science 2023-05-17 Itai Shapira

Modern CNNs' high computational demands hinder edge deployment, as traditional ``hard'' sparsity (skipping mathematical zeros) loses effectiveness in deep layers or with smooth activations like Tanh. We propose a ``soft sparsity'' paradigm…

Machine Learning · Computer Science 2026-04-10 Vishal Shashidhar , Anupam Kumari , Roy P Paily

Recently there has been much interest in understanding why deep neural networks are preferred to shallow networks. We show that, for a large class of piecewise smooth functions, the number of neurons needed by a shallow network to…

Machine Learning · Computer Science 2017-03-07 Shiyu Liang , R. Srikant

Accurate segmentation of thalamic nuclei is important for better understanding brain function and improving disease treatment. Traditional segmentation methods often rely on a single T1-weighted image, which has limited contrast in the…

Image and Video Processing · Electrical Eng. & Systems 2024-09-12 Anqi Feng , Zhangxing Bian , Blake E. Dewey , Alexa Gail Colinco , Jiachen Zhuo , Jerry L. Prince

In this article we identify a general class of high-dimensional continuous functions that can be approximated by deep neural networks (DNNs) with the rectified linear unit (ReLU) activation without the curse of dimensionality. In other…

Numerical Analysis · Mathematics 2023-04-13 Adrian Riekert

Nonlinear activation functions are widely recognized for enhancing the expressivity of neural networks, which is the primary reason for their widespread implementation. In this work, we focus on ReLU activation and reveal a novel and…

Machine Learning · Computer Science 2025-10-22 Chaoyue Liu , Han Bi , Like Hui , Xiao Liu

Rational exponential integrators (REXI) are a class of numerical methods that are well suited for the time integration of linear partial differential equations with imaginary eigenvalues. Since these methods can be parallelized in time (in…

Numerical Analysis · Mathematics 2021-04-28 Marco Caliari , Lukas Einkemmer , Alexander Moriggl , Alexander Ostermann

The development of Kolmogorov-Arnold networks (KANs) marks a significant shift from traditional multi-layer perceptrons in deep learning. Initially, KANs employed B-spline curves as their primary basis function, but their inherent…

Machine Learning · Computer Science 2024-06-21 Alireza Afzal Aghaei

Amongst others, the adoption of Rectified Linear Units (ReLUs) is regarded as one of the ingredients of the success of deep learning. ReLU activation has been shown to mitigate the vanishing gradient issue, to encourage sparsity in the…

Machine Learning · Statistics 2021-10-14 Nicola Picchiotti , Marco Gori

The widespread use of Multi-layer perceptrons (MLPs) often relies on a fixed activation function (e.g., ReLU, Sigmoid, Tanh) for all nodes within the hidden layers. While effective in many scenarios, this uniformity may limit the networks…

Machine Learning · Computer Science 2025-04-28 Hy Nguyen , Duy Khoa Pham , Srikanth Thudumu , Hung Du , Rajesh Vasa , Kon Mouzakis

The non-convex nature of trained neural networks has created significant obstacles in their incorporation into optimization models. In this context, Anderson et al. (2020) provided a framework to obtain the convex hull of the graph of a…

Optimization and Control · Mathematics 2026-04-01 Pablo Carrasco , Gonzalo Muñoz

We introduce S++, a simple, robust, and deployable framework for training a neural network (NN) using private data from multiple sources, using secret-shared secure function evaluation. In short, consider a virtual third party to whom every…

Cryptography and Security · Computer Science 2021-01-29 Prashanthi Ramachandran , Shivam Agarwal , Arup Mondal , Aastha Shah , Debayan Gupta

Replacing non-polynomial functions (e.g., non-linear activation functions such as ReLU) in a neural network with their polynomial approximations is a standard practice in privacy-preserving machine learning. The resulting neural network,…

Machine Learning · Computer Science 2024-06-10 Chi Zhang , Jingjing Fan , Man Ho Au , Siu Ming Yiu

Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation functions. Various new activation functions and improvements on…

Machine Learning · Computer Science 2019-08-27 Yang Liu , Jianpeng Zhang , Chao Gao , Jinghua Qu , Lixin Ji

Transformers have found extensive applications across various domains due to the powerful fitting capabilities. This success can be partially attributed to their inherent nonlinearity. Thus, in addition to the ReLU function employed in the…

Computation and Language · Computer Science 2025-03-21 Zhijian Zhuo , Ya Wang , Yutao Zeng , Xiaoqing Li , Xun Zhou , Jinwen Ma

Deep neural networks (DNNs) generate much richer function spaces than shallow networks. Since the function spaces induced by shallow networks have several approximation theoretic drawbacks, this explains, however, not necessarily the…

Machine Learning · Statistics 2018-09-25 Konstantin Eckle , Johannes Schmidt-Hieber

In recent years, the computational demands of deep learning applications have necessitated the introduction of energy-efficient hardware accelerators. Optical neural networks are a promising option; however, thus far they have been largely…

While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small proportion of samples from unlabeled data for labeling and…

Machine Learning · Computer Science 2022-07-20 Xueying Zhan , Qingzhong Wang , Kuan-hao Huang , Haoyi Xiong , Dejing Dou , Antoni B. Chan

Nonlinear activation functions are pivotal to the success of deep neural nets, and choosing the appropriate activation function can significantly affect their performance. Most networks use fixed activation functions (e.g., ReLU, GELU,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Irit Chelly , Shahaf E. Finder , Shira Ifergane , Oren Freifeld

Recurrent Neural Network (RNN) applications form a major class of AI-powered, low-latency data center workloads. Most execution models for RNN acceleration break computation graphs into BLAS kernels, which lead to significant inter-kernel…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-10-01 Tian Zhao , Yaqi Zhang , Kunle Olukotun