English
Related papers

Related papers: SERF: Towards better training of deep neural netwo…

200 papers

Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) has demonstrated that alternatives are possible. The point-wise function DyT…

Machine Learning · Computer Science 2026-04-01 Mingzhi Chen , Taiming Lu , Jiachen Zhu , Mingjie Sun , Zhuang Liu

In this article we study high-dimensional approximation capacities of shallow and deep artificial neural networks (ANNs) with the rectified linear unit (ReLU) activation. In particular, it is a key contribution of this work to reveal that…

Numerical Analysis · Mathematics 2023-01-23 Lukas Gonon , Robin Graeber , Arnulf Jentzen

We propose ReDense as a simple and low complexity way to improve the performance of trained neural networks. We use a combination of random weights and rectified linear unit (ReLU) activation function to add a ReLU dense (ReDense) layer to…

Machine Learning · Computer Science 2020-10-27 Alireza M. Javid , Sandipan Das , Mikael Skoglund , Saikat Chatterjee

This document proposes a parametric activation function (ac.f.) aimed at improving multidimensional nonlinear data regression. It is a established knowledge that nonlinear ac.f's are required for learning nonlinear datasets. This work shows…

Machine Learning · Computer Science 2025-10-03 Enda D. V. Bigarella

This paper introduces a novel parametric activation function based on Wendland radial basis functions (RBFs) for deep neural networks. Wendland RBFs, known for their compact support, smoothness, and positive definiteness in approximation…

Machine Learning · Computer Science 2025-07-16 Majid Darehmiraki

Many industrial and real life problems exhibit highly nonlinear periodic behaviors and the conventional methods may fall short of finding their analytical or closed form solutions. Such problems demand some cutting edge computational tools…

Machine Learning · Computer Science 2023-04-20 Jamshaid Ul Rahman , Faiza Makhdoom , Dianchen Lu

For many machine learning applications, a common input representation is a spectrogram. The underlying representation for a spectrogram is a short time Fourier transform (STFT) which gives complex values. The spectrogram uses the magnitude…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-28 Les Atlas , Nicholas Rasmussen , Felix Schwock , Mert Pilanci

LayerNorm is a critical component in modern large language models (LLMs) for stabilizing training and ensuring smooth optimization. However, it introduces significant challenges in mechanistic interpretability, outlier feature suppression,…

Machine Learning · Computer Science 2024-11-19 Nandan Kumar Jha , Brandon Reagen

Stable and efficient training of ReLU networks with large depth is highly sensitive to weight initialization. Improper initialization can cause permanent neuron inactivation dying ReLU and exacerbate gradient instability as network depth…

Machine Learning · Computer Science 2025-09-03 Hyungu Lee , Taehyeong Kim , Hayoung Choi

Self Normalizing Neural Networks(SNN) proposed on Feed Forward Neural Networks(FNN) outperform regular FNN architectures in various machine learning tasks. Particularly in the domain of Computer Vision, the activation function Scaled…

Computation and Language · Computer Science 2019-05-07 Avinash Madasu , Vijjini Anvesh Rao

A new network with super approximation power is introduced. This network is built with Floor ($\lfloor x\rfloor$) or ReLU ($\max\{0,x\}$) activation function in each neuron and hence we call such networks Floor-ReLU networks. For any…

Machine Learning · Computer Science 2021-03-30 Zuowei Shen , Haizhao Yang , Shijun Zhang

The efficacy of deep learning models has been called into question by the presence of adversarial examples. Addressing the vulnerability of deep learning models to adversarial examples is crucial for ensuring their continued development and…

Machine Learning · Computer Science 2024-05-08 Korn Sooksatra , Greg Hamerly , Pablo Rivas

Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that…

Machine Learning · Computer Science 2017-03-06 Bo Xie , Yingyu Liang , Le Song

Deep neural networks paved the way for significant improvements in image visual categorization during the last years. However, even though the tasks are highly varying, differing in complexity and difficulty, existing solutions mostly build…

Machine Learning · Computer Science 2019-10-29 Mina Basirat , Peter M. Roth

In spite of finite dimension ReLU neural networks being a consistent factor behind recent deep learning successes, a theory of feature learning in these models remains elusive. Currently, insightful theories still rely on assumptions…

Machine Learning · Computer Science 2025-04-01 Devon Jarvis , Richard Klein , Benjamin Rosman , Andrew M. Saxe

The Transformer architecture consists of self-attention and feed-forward networks (FFNs) which can be viewed as key-value memories according to previous works. However, FFN and traditional memory utilize different activation functions…

Computation and Language · Computer Science 2023-02-14 Kai Shen , Junliang Guo , Xu Tan , Siliang Tang , Rui Wang , Jiang Bian

We theoretically discuss why deep neural networks (DNNs) performs better than other models in some cases by investigating statistical properties of DNNs for non-smooth functions. While DNNs have empirically shown higher performance than…

Machine Learning · Statistics 2018-07-10 Masaaki Imaizumi , Kenji Fukumizu

Neural networks are powerful functions with widespread use, but the theoretical behaviour of these functions is not fully understood. Creating deep neural networks by stacking many layers has achieved exceptional performance in many…

Machine Learning · Computer Science 2024-08-16 Cameron Jakub , Mihai Nica

We propose a novel Shapley value approach to help address neural networks' interpretability and "vanishing gradient" problems. Our method is based on an accurate analytical approximation to the Shapley value of a neuron with ReLU…

Machine Learning · Statistics 2019-09-18 Yadong Li , Xin Cui

Deep neural networks have been successfully used in diverse emerging domains to solve real world complex problems with may more deep learning(DL) architectures, being developed to date. To achieve these state-of-the-art performances, the DL…

Machine Learning · Computer Science 2018-11-09 Chigozie Nwankpa , Winifred Ijomah , Anthony Gachagan , Stephen Marshall